{
  "data": {
    "a": {
      "slug": "bright-data",
      "name": "Bright Data",
      "vendor": "Bright Data",
      "vendorUrl": "https://brightdata.com",
      "company": "brightdata.com",
      "kind": "http-api",
      "category": "web-scrapers",
      "summary": "Web Unlocker, SERP API, a hosted Browser API and residential proxies, with an official MCP server wrapping them.",
      "url": "https://www.anchorterminal.com/tools/bright-data",
      "markdownUrl": "https://www.anchorterminal.com/tools/bright-data.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/bright-data.min.md",
      "cardUrl": "https://www.anchorterminal.com/tools/bright-data.card.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/bright-data.json",
      "dns": "bright-data.grade.anchorterminal.com",
      "repo": "https://github.com/brightdata/brightdata-mcp",
      "transports": [
        "http",
        "streamable-http"
      ],
      "remoteUrl": "https://api.brightdata.com/request",
      "packages": [
        {
          "registry": "npm",
          "name": "@brightdata/mcp"
        }
      ],
      "auth": "mixed",
      "authNotes": "Bearer key for the API. Keys take a role (Admin, Finance, Ops, Limit or User) and an optional expiry. Proxy-style access uses Basic auth on port 44445. The hosted MCP takes the key as `?token=` in the URL by default, or OAuth 2.1 (PKCE S256, scope `mcp`) with an `Authorization: Bearer` header. MCP agent keys are listed separately in account settings and can be revoked.",
      "pricing": "freemium",
      "pricingNotes": "5,000 free requests a month including MCP, no card. Web Unlocker and SERP $1.50 per 1,000 successful requests, $1.30 on Scale ($499 a month). Browser API $8 a GB (https://brightdata.com/pricing).",
      "priceSummary": "$1.50 / 1k req",
      "where": "hosted",
      "x402": {
        "level": "no",
        "endpoints": []
      },
      "toolCount": 32,
      "popularity": {
        "githubStars": 2600,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-09-26"
      },
      "docsUrl": "https://docs.brightdata.com",
      "llmsTxt": "https://docs.brightdata.com/llms.txt",
      "registryName": "io.github.brightdata/brightdata-mcp",
      "capabilities": [
        "web.scrape",
        "web.search",
        "browser.hosted",
        "web.crawl"
      ],
      "tags": [
        "hosted",
        "freemium",
        "no-card",
        "mcp",
        "llms-txt",
        "proxies"
      ],
      "lastRelease": "2026-11-02",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 59.4,
        "grade": "C",
        "agentReady": false,
        "rank": 816,
        "ranked": true,
        "rankOf": 1563,
        "categoryRank": 21,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 79,
          "maintenance": 87,
          "payments": 60,
          "reliability": 40,
          "schema": 74,
          "security": 69,
          "transparency": 61
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-04"
        },
        "negative": -6,
        "negativeNotes": [
          "1 and 2 November 2026. MCP 4.2.0 and 4.3.0, minor releases of the 4.x `@brightdata/mcp` package, changed published tool behaviour with no earlier notice found. 4.2.0 made `scrape_as_markdown` and `scrape_batch` return JSON instead of Markdown and dropped JavaScript rendering; 4.3.0 renamed `geo_location` to `country` and `cursor` to `page`, with the old names returning an `invalid_input` error, and removed Yandex. One term for breaking changes in a minor release without notice, -3 (https://github.com/brightdata/brightdata-mcp/blob/main/CHANGELOG.md).",
          "19 October 2026. The release notes say Immediate access Residential and Mobile proxies are no longer supported, \"effective 19-October-2026\", in an entry dated that day, and that unused proxies on accounts without KYC were deleted. Requests through those zones stopped working with notice only on the day (the 24 October entry gave 9 November for deleting the rest). Same-day change, -3 (https://docs.brightdata.com/release-notes)."
        ],
        "verdict": "Bright Data bills only successful requests, $1.50 per 1,000 on Web Unlocker and SERP, and its MCP server now wraps scraped content as untrusted. There's no public status page or incident history, and MCP 4.2.0 and 4.3.0 changed tool inputs and outputs in minor releases without notice.",
        "bestFor": "Hard targets and site-specific structured data (Amazon, LinkedIn, Instagram, Google Maps) at volume.",
        "strengths": [
          "Pay only for successful requests, $1.50 per 1,000 on Web Unlocker and SERP",
          "5,000 free requests a month with no card",
          "MCP results are wrapped as untrusted web content, and a content gate asks the user before returning instruction-like page text",
          "Role-based API keys with expiry, and OAuth 2.1 with PKCE on the hosted MCP",
          "Every MCP tool carries readOnlyHint and destructiveHint, and the registry entry matches the latest release"
        ],
        "weaknesses": [
          "No public status page or incident history",
          "The default hosted MCP URL carries the key as `?token=`",
          "All 32 MCP tools load by default since 3.1.0, browser click and type among them",
          "MCP 4.2.0 and 4.3.0 changed tool output and renamed inputs in minor releases without notice",
          "No retention periods, DPA or subprocessor list in the privacy policy"
        ],
        "agentNotes": [
          "Connect with OAuth or keep the `?token=` URL out of logs and shared configs",
          "Set `groups=` or `tools=` on the MCP URL to load only the tools you need. With neither, all 32 load",
          "Send `country` and `page` to the search tools from 4.3.0. `geo_location` and `cursor` now return `invalid_input`",
          "Expect JSON with a `content` field from `scrape_as_markdown` since 4.2.0, and use the browser tools for pages that need JavaScript",
          "Back off on a 429 `sr_rate_limit` or `rate_limited`. Bright Data throttles a target whose success rate drops"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 2,
        "avgRating": 4,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "C",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 59.4
          }
        ],
        "editorialScores": {
          "ergonomics": 79,
          "maintenance": 87,
          "payments": 60,
          "reliability": 40,
          "schema": 74,
          "security": 69,
          "transparency": 43
        },
        "provenanceScore": 79,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-04",
            "maintenance": "2026-11-04",
            "payments": "2026-11-04",
            "reliability": "2026-11-04",
            "schema": "2026-11-04",
            "security": "2026-11-04",
            "transparency": "2026-11-04"
          },
          "last": "2026-11-04",
          "lastMoved": "2026-11-13",
          "oldest": "2026-11-04",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "http": "curl https://api.brightdata.com/request -H \"Authorization: Bearer $BRIGHTDATA_TOKEN\" \\\n  -H \"content-type: application/json\" -d '{\"zone\":\"web_unlocker1\",\"url\":\"https://example.com\",\"format\":\"raw\"}'",
        "claudeCode": "claude mcp add --transport http brightdata \"https://mcp.brightdata.com/mcp?token=$BRIGHTDATA_TOKEN\""
      },
      "letme": {
        "capability": "https://letme.dev/web.scrape",
        "tool": "https://letme.dev/bright-data"
      },
      "area": "web-data",
      "unitPrices": [
        {
          "item": "Web Unlocker",
          "unit": "1k-requests",
          "usd": 1.5,
          "note": "successful requests only"
        },
        {
          "item": "Web Unlocker on Scale",
          "unit": "1k-requests",
          "usd": 1.3,
          "note": "$499 a month plan"
        },
        {
          "item": "SERP API",
          "unit": "1k-requests",
          "usd": 1.5
        },
        {
          "item": "Browser API",
          "unit": "gb",
          "usd": 8
        }
      ],
      "provenance": {
        "legalEntity": "Bright Data Ltd.",
        "domain": "brightdata.com",
        "domainRegistered": "2002-05-26",
        "domainNote": "brightdata.com was registered in 2002, long before the rename from Luminati.",
        "endpointOnVendorDomain": true,
        "terms": "https://brightdata.com/license",
        "privacy": "https://brightdata.com/privacy",
        "statusPage": "",
        "changelog": "https://docs.brightdata.com/release-notes",
        "securityTxt": "none",
        "checked": "2026-11-04",
        "notes": [
          "The Master Service Agreement at brightdata.com/license was last updated 12 October 2026 and names Bright Data Ltd., 4 Hamahshev St., Netanya, Israel.",
          "status.brightdata.com doesn't resolve and no status page is linked (4 November 2026).",
          "brightdata.com/.well-known/security.txt answers 404 (4 November 2026).",
          "brightdata.com's robots.txt allows ClaudeBot, sets Crawl-delay 5 for other agents and carries `Content-Signal: search=yes, ai-input=yes, ai-train=yes`."
        ],
        "score": 79
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/bright-data.json",
      "live": {
        "slug": "bright-data",
        "probe": {
          "target": "https://api.brightdata.com/request",
          "method": "get",
          "lastAt": "2026-11-20T21:48:34.153153186Z",
          "lastOk": true,
          "lastStatus": 404,
          "lastMs": 306,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 99.42,
          "p50ms24h": 294,
          "p95ms24h": 406,
          "samples24h": 242,
          "samples30d": 7801,
          "days": [
            {
              "date": "2026-10-20",
              "probes": 252,
              "ok": 249
            },
            {
              "date": "2026-10-21",
              "probes": 253,
              "ok": 253
            },
            {
              "date": "2026-10-22",
              "probes": 253,
              "ok": 253
            },
            {
              "date": "2026-10-23",
              "probes": 248,
              "ok": 246
            },
            {
              "date": "2026-10-24",
              "probes": 251,
              "ok": 251
            },
            {
              "date": "2026-10-25",
              "probes": 250,
              "ok": 249
            },
            {
              "date": "2026-10-26",
              "probes": 252,
              "ok": 252
            },
            {
              "date": "2026-10-27",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-28",
              "probes": 251,
              "ok": 251
            },
            {
              "date": "2026-10-29",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-30",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-10-31",
              "probes": 251,
              "ok": 250
            },
            {
              "date": "2026-11-01",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-11-02",
              "probes": 250,
              "ok": 250
            },
            {
              "date": "2026-11-03",
              "probes": 248,
              "ok": 219
            },
            {
              "date": "2026-11-04",
              "probes": 246,
              "ok": 246
            },
            {
              "date": "2026-11-05",
              "probes": 185,
              "ok": 184
            },
            {
              "date": "2026-11-06",
              "probes": 241,
              "ok": 240
            },
            {
              "date": "2026-11-07",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-08",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-09",
              "probes": 243,
              "ok": 242
            },
            {
              "date": "2026-11-10",
              "probes": 244,
              "ok": 243
            },
            {
              "date": "2026-11-11",
              "probes": 244,
              "ok": 243
            },
            {
              "date": "2026-11-12",
              "probes": 245,
              "ok": 242
            },
            {
              "date": "2026-11-13",
              "probes": 238,
              "ok": 238
            },
            {
              "date": "2026-11-14",
              "probes": 244,
              "ok": 243
            },
            {
              "date": "2026-11-15",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-16",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-17",
              "probes": 242,
              "ok": 242
            },
            {
              "date": "2026-11-18",
              "probes": 240,
              "ok": 240
            },
            {
              "date": "2026-11-19",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-20",
              "probes": 220,
              "ok": 220
            }
          ],
          "outages": [
            {
              "start": "2026-11-03T14:39:35.223756527Z",
              "end": "2026-11-03T15:48:49.987146062Z",
              "note": "HTTP 502 server error"
            },
            {
              "start": "2026-11-03T13:35:58.075019639Z",
              "end": "2026-11-03T14:04:32.666176656Z",
              "note": "HTTP 502 server error"
            },
            {
              "start": "2026-11-03T13:06:26.66673786Z",
              "end": "2026-11-03T13:23:54.312023692Z",
              "note": "HTTP 502 server error"
            },
            {
              "start": "2026-11-03T12:24:31.574115633Z",
              "end": "2026-11-03T13:00:48.514456897Z",
              "note": "HTTP 504 server error"
            }
          ],
          "since": "2026-10-08T00:00:00Z"
        },
        "versions": [
          {
            "registry": "github",
            "name": "brightdata/brightdata-mcp",
            "version": "v4.8.0",
            "released": "2026-11-10",
            "seenAt": "2026-11-20T20:17:47.709696542Z"
          },
          {
            "registry": "mcp-registry",
            "name": "io.github.brightdata/brightdata-mcp",
            "version": "4.8.0",
            "seenAt": "2026-11-19T23:10:32.423145357Z"
          },
          {
            "registry": "npm",
            "name": "@brightdata/mcp",
            "version": "4.8.0",
            "seenAt": "2026-11-20T20:17:47.327644688Z"
          }
        ],
        "githubStars": 2732,
        "npmWeekly": 9494,
        "securityTxt": {
          "url": "https://brightdata.com/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-11-20T16:36:28.767593855Z"
        },
        "llmsTxt": {
          "url": "https://docs.brightdata.com/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-11-20T16:21:46.46354445Z"
        },
        "domain": {
          "domain": "brightdata.com",
          "registered": "2002-05-26",
          "source": "https://rdap.verisign.com/com/v1/domain/brightdata.com",
          "checkedAt": "2026-11-15T15:20:35.516084646Z"
        },
        "pages": [
          {
            "url": "https://brightdata.com/license",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-11-19T22:15:21.116761792Z",
            "changedAt": "2026-11-19T22:15:21.116761792Z",
            "fingerprint": "a5a602b7f462"
          },
          {
            "url": "https://docs.brightdata.com/release-notes",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-11-19T22:20:09.837874173Z",
            "changedAt": "2026-11-19T22:20:09.837874173Z",
            "fingerprint": "aaa913e803ca"
          },
          {
            "url": "https://raw.githubusercontent.com/brightdata/brightdata-mcp/main/CHANGELOG.md",
            "kind": "deprecations",
            "status": 304,
            "checkedAt": "2026-11-19T22:35:41.445457876Z",
            "changedAt": "2026-11-18T21:54:28.607691019Z",
            "fingerprint": "e70af46d4d5a"
          },
          {
            "url": "https://brightdata.com/pricing",
            "kind": "pricing",
            "status": 200,
            "checkedAt": "2026-11-19T22:15:23.410201705Z",
            "changedAt": "2026-11-19T22:15:23.410201705Z",
            "fingerprint": "fc3c8c85cd92"
          },
          {
            "url": "https://brightdata.com/privacy",
            "kind": "privacy",
            "status": 200,
            "checkedAt": "2026-11-19T22:15:25.411409433Z",
            "changedAt": "2026-11-19T22:15:25.411409433Z",
            "fingerprint": "4707d7f4c0a4"
          }
        ],
        "mcpTools": {
          "url": "https://mcp.brightdata.com/mcp?token=$BRIGHTDATA_TOKEN",
          "checkedAt": "2026-11-20T04:51:59.487495794Z",
          "status": "auth",
          "note": "asks for credentials before listing its tools",
          "changedAt": "2026-11-07T01:42:54.215567368Z"
        },
        "github": {
          "repo": "brightdata/brightdata-mcp",
          "checkedAt": "2026-11-16T11:48:37.848442806Z",
          "stars": 2729,
          "archived": false,
          "issuesEnabled": true,
          "pushedAt": "2026-11-12T15:18:36Z",
          "openIssues": 16,
          "openPRs": 23,
          "issuesOpened90d": 7,
          "issuesClosed90d": 1,
          "prsMerged90d": 14,
          "ci": {
            "branch": "main",
            "runs": 50,
            "success": 50,
            "failure": 0,
            "other": 0,
            "latest": "success",
            "latestAt": "2026-11-12T15:19:21Z"
          },
          "replies": {
            "sampled": 25,
            "unanswered": 13,
            "medianDays": 3.2
          }
        },
        "updatedAt": "2026-11-20T21:48:34.153153186Z"
      },
      "streak": {
        "days": 11,
        "from": "2026-11-09",
        "last": {
          "kind": "shutdown",
          "date": "2026-11-09",
          "what": "Retired Immediate access Residential and Mobile proxies are deleted from customer accounts. Move to ISP Proxies or the Web Unlocker API first",
          "source": "https://docs.brightdata.com/release-notes"
        },
        "best": 13
      }
    },
    "answer": "Bright Data scores 59.4 (C) on agent readiness against XCrawl's 30.4 (F), and leads in every scored category.",
    "b": {
      "slug": "xcrawl",
      "name": "XCrawl",
      "vendor": "XCrawl",
      "vendorUrl": "https://www.xcrawl.com/",
      "company": "xcrawl.com",
      "kind": "http-api",
      "category": "web-scrapers",
      "summary": "XCrawl is a hosted web scraping API from Xcrawl LLC with scrape, search, map, crawl and site-specific data endpoints that return Markdown, HTML, JSON or screenshots, through REST, Python and Node.js SDKs and a hosted MCP server.",
      "url": "https://www.anchorterminal.com/tools/xcrawl",
      "markdownUrl": "https://www.anchorterminal.com/tools/xcrawl.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/xcrawl.min.md",
      "cardUrl": "https://www.anchorterminal.com/tools/xcrawl.card.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/xcrawl.json",
      "dns": "xcrawl.grade.anchorterminal.com",
      "repo": "https://github.com/xcrawl-api/xcrawl-sdk",
      "transports": [
        "streamable-http",
        "stdio"
      ],
      "remoteUrl": "https://mcp.xcrawl.com/{YOUR_API_KEY}/mcp",
      "packages": [
        {
          "registry": "pypi",
          "name": "xcrawl"
        },
        {
          "registry": "npm",
          "name": "@xcrawl/xcrawl"
        },
        {
          "registry": "npm",
          "name": "xcrawl-mcp"
        }
      ],
      "auth": "api-key",
      "authNotes": "Bearer API key (`Authorization: Bearer \u003capi_key\u003e`) from the dashboard at dash.xcrawl.com after a browser signup. No scopes, expiry or rotation documented. The MCP guide says to reissue an invalid key in the dashboard. The hosted MCP server takes the key in the URL path (`https://mcp.xcrawl.com/{YOUR_API_KEY}/mcp`), which the docs give as the recommended setup.",
      "pricing": "freemium",
      "pricingNotes": "1,000 free credits on signup with no card, per the home page, pricing page FAQ and the skills repository. Paid plans are monthly or yearly subscriptions, with Scale plans through sales, but the plan prices and credit table did not appear in the served pricing page (unchecked). Doc examples show a plain scrape at 1 credit and a search at 2.",
      "priceSummary": "Freemium",
      "where": "both",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the docs, the pricing page, the SDKs or the skills repository (checked 2026-11-20). Accounts are made and paid for in the dashboard.",
        "endpoints": []
      },
      "toolCount": 7,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-20"
      },
      "docsUrl": "https://docs.xcrawl.com/",
      "capabilities": [
        "web.scrape",
        "web.extract",
        "web.crawl",
        "scraping.proxies",
        "scraping.js-render",
        "scraping.anti-bot",
        "web.search",
        "search.serp"
      ],
      "tags": [
        "hosted",
        "freemium",
        "no-card",
        "free-tier",
        "mcp",
        "remote-mcp",
        "proxies",
        "python",
        "typescript"
      ],
      "lastRelease": "2026-04-13",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 30.4,
        "grade": "F",
        "agentReady": false,
        "rank": 1463,
        "ranked": true,
        "rankOf": 1563,
        "categoryRank": 35,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 59,
          "maintenance": 17,
          "payments": 30,
          "reliability": 15,
          "schema": 35,
          "security": 18,
          "transparency": 43
        },
        "assessment": {
          "confidence": "low",
          "date": "2026-11-20"
        },
        "negative": 0,
        "warnings": [
          {
            "kind": "operator-unidentified",
            "name": "Operator not identified",
            "text": "XCrawl's home page footer and terms name Xcrawl LLC, with no state of registration, registration number or address. Wyoming's business search needs a form our reader can't submit, a trademark directory naming a Sheridan, Wyoming address closed itself to our reader, and no register entry was found.",
            "deduct": 0,
            "capGrade": "B",
            "since": "2026-11-20",
            "sources": [
              "https://www.xcrawl.com/",
              "https://www.xcrawl.com/terms-of-service/",
              "https://www.xcrawl.com/privacy-policy/",
              "https://wyobiz.wyo.gov/Business/FilingSearch.aspx"
            ]
          }
        ],
        "verdict": "A scrape, search, map and crawl API with 7 MCP tools, MIT Python and Node.js SDKs and 1,000 free credits without a card. Xcrawl LLC gives no address or registration. There is no OpenAPI spec, status page, rate limit, error reference or changelog, plan prices did not render for us, and the hosted MCP key travels in the URL.",
        "bestFor": "A general scrape, crawl, map and SERP API for agents, with 35 site-specific data endpoints.",
        "strengths": [
          "1,000 free credits on signup with no card, per the home page and pricing FAQ",
          "Seven MCP tools covering scrape, search, map, crawl, key balance and job status, hosted or through `npx xcrawl-mcp`",
          "Each response reports credits used with a base, traffic and JSON extraction breakdown",
          "Crawl takes page limits, depth and include or exclude regex patterns, and search takes a 1 to 100 result limit",
          "Python `xcrawl` and Node.js `@xcrawl/xcrawl` SDKs under MIT, version 1.1.2"
        ],
        "weaknesses": [
          "Xcrawl LLC is named with no state, registration number or address, and the terms name no governing law",
          "No OpenAPI spec, llms.txt, error reference, rate limits or changelog in the docs",
          "No status page, SLA or security.txt. The home page shows ISO 27001 and \"CDPR\" badges with no certificate or security page behind them",
          "The hosted MCP server takes the API key in its URL path, and the MCP package is closed source",
          "No SDK or MCP release since 13 April 2026"
        ],
        "agentNotes": [
          "Use the `npx xcrawl-mcp` setup with `XCRAWL_API_KEY` in the environment rather than the hosted URL, which puts the key in the path",
          "Set `skip_tls_verification` to false when the page's certificate matters, because scrape and crawl default it to true",
          "Set `crawler.limit` and `max_depth` on every crawl, since the defaults are 100 pages and depth 3",
          "Call xcrawl_key_status before a large crawl, because the docs give no credit table to estimate the cost",
          "Treat scraped Markdown and JSON as untrusted page content, since the docs give no prompt-injection guidance"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "low",
            "grade": "F",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 30.4
          }
        ],
        "editorialScores": {
          "ergonomics": 59,
          "maintenance": 17,
          "payments": 30,
          "reliability": 15,
          "schema": 35,
          "security": 18,
          "transparency": 21
        },
        "provenanceScore": 64,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-20",
            "maintenance": "2026-11-20",
            "payments": "2026-11-20",
            "reliability": "2026-11-20",
            "schema": "2026-11-20",
            "security": "2026-11-20",
            "transparency": "2026-11-20"
          },
          "last": "2026-11-20",
          "oldest": "2026-11-20",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "pip install xcrawl",
        "http": "curl -X POST https://run.xcrawl.com/v1/scrape -H \"Authorization: Bearer $XCRAWL_API_KEY\" -H \"Content-Type: application/json\" -d '{\"url\":\"https://example.com\",\"output\":{\"formats\":[\"markdown\"]}}'",
        "claudeCode": "claude mcp add xcrawl -e XCRAWL_API_KEY=YOUR_XCRAWL_API_KEY -- npx -y xcrawl-mcp",
        "config": {
          "mcpServers": {
            "xcrawl": {
              "args": [
                "-y",
                "xcrawl-mcp"
              ],
              "command": "npx",
              "env": {
                "XCRAWL_API_KEY": "YOUR_XCRAWL_API_KEY"
              }
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/web.scrape",
        "tool": "https://letme.dev/xcrawl"
      },
      "area": "web-data",
      "provenance": {
        "legalEntity": "Xcrawl LLC",
        "domain": "xcrawl.com",
        "domainRegistered": "2006-12-29",
        "endpointOnVendorDomain": true,
        "terms": "https://www.xcrawl.com/terms-of-service/",
        "privacy": "https://www.xcrawl.com/privacy-policy/",
        "statusPage": "",
        "changelog": "",
        "securityTxt": "none",
        "checked": "2026-11-20",
        "notes": [
          "www.xcrawl.com/robots.txt allows all agents except /api/. docs.xcrawl.com/robots.txt allows all. mcp.xcrawl.com/robots.txt asked for a sign-in, so nothing was sent to the MCP host. www.xcrawl.ai/robots.txt disallows ClaudeBot, anthropic-ai and Claude-Web and carries `Content-Signal: search=yes,ai-train=no,use=reference`.",
          "RDAP gives xcrawl.com a registration date of 29 December 2006, last changed 14 July 2026. The SDKs and MCP package date from 12 February 2026.",
          "The terms carry no effective date or governing law and mention arbitration and class action clauses without their text. The refund policy is effective 14 November 2025 and allows one refund within 7 days of a first purchase.",
          "The terms say some services need a compliance review that may include know-your-customer checks and a video call, and forbid crawling financial, banking or cryptocurrency exchange sites.",
          "/.well-known/security.txt returns 404. No status page or changelog found."
        ],
        "score": 64
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/xcrawl.json",
      "live": {
        "slug": "xcrawl",
        "versions": [
          {
            "registry": "npm",
            "name": "@xcrawl/xcrawl",
            "version": "1.1.2",
            "seenAt": "2026-11-20T21:26:27.199324752Z"
          },
          {
            "registry": "npm",
            "name": "xcrawl-mcp",
            "version": "1.0.6",
            "seenAt": "2026-11-20T21:26:27.640797999Z"
          },
          {
            "registry": "pypi",
            "name": "xcrawl",
            "version": "1.1.2",
            "released": "2026-04-13",
            "seenAt": "2026-11-20T21:26:27.01532389Z"
          }
        ],
        "githubStars": 2,
        "npmWeekly": 8,
        "pypiWeekly": 123,
        "securityTxt": {
          "url": "https://xcrawl.com/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-11-20T16:36:09.372956779Z"
        },
        "updatedAt": "2026-11-20T21:26:29.494850121Z"
      }
    },
    "edges": [
      {
        "by": 70,
        "category": "maintenance",
        "leads": "bright-data",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "MCP v4.3.0 on 2 November 2026 (30). Ten MCP releases since 6 August, 2.11.2 (11 September), 2.11.3 (15 September), 2.12.0 (8 October), 3.0.0 (11 October), 3.1.0 (15 October), 4.0.0 (18 October), 4.1.0 (20 October), 4.1.1 (29 October), 4.2.0 (1 November) and 4.3.0, and product release notes dated 19, 24 and 27 October (20). Issues not read (GitHub's pages refuse our reader); outside pull requests such as #200 were merged within a week, and the 1 October count of 13 open issues stands (12 of 25). io.github.brightdata/brightdata-mcp in the official registry under a GitHub-verified namespace, now at 4.3.0, the latest release (15). Tests run in CI on every push, and the release workflow runs the tests and `npm audit signatures` before publishing with provenance (10). 30+20+12+15+10 = 87.",
          "b": "The newest dated releases are the Python SDK 1.1.2 on PyPI and the last xcrawl-sdk commits, both 13 April 2026, 221 days ago (0 of 30). Nothing dated in the 90 days from 22 August 2026 (0 of 20). We couldn't read GitHub issues. There is no public changelog, and support is by email, Telegram, WhatsApp and Microsoft Teams, with a 24-hour reply promised in the footer (5 of 15). Official Python and Node.js SDKs, unchanged for seven months (10 of 15). The SDK repository has 3 commits, no tests and no CI. Dependencies are current (2 of 10). Total 17."
        },
        "scores": {
          "a": 87,
          "b": 17
        }
      },
      {
        "by": 51,
        "category": "security",
        "leads": "bright-data",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "API keys carry one of five roles (Admin, Finance, Ops, Limit, User), can be given an expiry, and are revoked or refreshed in the control panel, and the hosted MCP also takes OAuth 2.1 with PKCE and one `mcp` scope (30). The README's default hosted setup still puts the key in the URL as `?token=`, a documented option, so less 10 (20). User-role keys can't change configuration, tools load by group, and tools carry readOnlyHint and destructiveHint, but browser tools can fill forms and click with no confirmation step from the server (14 of 20). Since 3.1.0 results from search, scrape, scraper, dataset and browser tools are wrapped as untrusted web content with a per-call marker, and since 2.12.0 a content gate, documented in the README and on by default, asks the user through MCP elicitation before returning page text that looks like instructions to change the MCP configuration (12 of 15). The MCP `session_stats` tool reports calls in a session. We didn't find a per-request log for operators (5 of 15). ISO 27001, 27017 and 27018, SOC 2 Type II under NDA, a public SOC 3, a managed private bug bounty and security fixes in the MCP changelog per the 1 October check. No security.txt (404 on 4 November). OSV holds no advisory for @brightdata/mcp (18 of 20). 20+14+12+5+18 = 69.",
          "b": "A plain bearer API key from the dashboard with no scopes, and the MCP guide says to reissue an invalid key there (20). The recommended hosted MCP setup puts the key in the URL path, so less 10, read the way the checklist reads a key in a query string (10 of 30). The API only reads third-party pages and has no destructive account actions, but there is no read-only or least-privilege key (5 of 20). No prompt-injection guidance in the docs or the skills (0 of 15). Each response reports credits used, and xcrawl_key_status gives the balance, with no request log found (3 of 15). No security.txt, disclosure policy or bug bounty. The ISO 27001 badge on the home page links to no certificate or security page (0 of 20). Total 18."
        },
        "scores": {
          "a": 69,
          "b": 18
        }
      },
      {
        "by": 39,
        "category": "schema",
        "leads": "bright-data",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "No OpenAPI file found for the API. The MCP server has zod schemas on every tool, so partial credit (15 of 25). llms.txt at docs.brightdata.com with Markdown pages (10). MCP descriptions say what each tool returns, and the dataset tools say when to use them instead of `run_scraper` (14 of 20). Typed inputs with enums such as engine (bing or google), time_range and format (12 of 15). Per-product error catalogues for Web Unlocker, Browser API and scrapers, and curl examples (13 of 15). Release notes, now dated to 27 October 2026, and an MCP CHANGELOG with a gap between 2.6.0 and 2.10.0, per the 1 October reading (10 of 15).",
          "b": "No OpenAPI or other machine-readable spec found, and the MCP package is closed source, so its tool schemas couldn't be read (0 of 25). llms.txt returns 404. The docs have \"Copy page\" buttons, and the xcrawl-skills repository has Markdown skill files for agents (5 of 10). Each API reference page states what the endpoint does, with no guidance on when not to use it (8 of 20). Parameter tables give types, required flags, defaults and enums for formats, device and wait_until. cookies and headers are free maps (11 of 15). Request and response examples on every reference page, but no error responses or codes documented outside the MCP troubleshooting table (6 of 15). Versioned /v1 paths and no changelog (5 of 15). Total 35."
        },
        "scores": {
          "a": 74,
          "b": 35
        }
      },
      {
        "by": 30,
        "category": "payments",
        "leads": "bright-data",
        "name": "Payments \u0026 pricing",
        "reasons": {
          "a": "No x402, MPP or L402. Issue #126 asks for x402 and is open (0). Web Unlocker and SERP at $1.50 per 1,000 successful requests, $1.30 on Scale, published without a login (20). 5,000 requests a month, 'No credit card required' (20). A person has to sign up and create a key in the control panel (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.",
          "b": "No x402, MPP or L402 (0). The pricing page's plan table and credit table did not appear in the served page, and the docs give credit costs only in examples (1 for a plain scrape, 2 for a search), so pricing is scored absent (0 of 30, unchecked). 1,000 free credits on signup with no card (30). A person signs up in a browser at dash.xcrawl.com to get a key (0). Total 30."
        },
        "scores": {
          "a": 60,
          "b": 30
        }
      },
      {
        "by": 25,
        "category": "reliability",
        "leads": "bright-data",
        "name": "Reliability",
        "reasons": {
          "a": "No public status page found. status.brightdata.com doesn't resolve and the docs index and security overview link none (0). No readable incident history, so 5 by the rubric (5). The SERP API fair-use page gives 1,000 requests a minute for unfunded accounts with HTTP 429 above it and a header that reads the account's limit, paid Web Unlocker plans state unlimited concurrency, and the free tier is 5,000 requests a month (15). The Web Unlocker error catalogue documents a 429 `sr_rate_limit` when Bright Data throttles a target with a low success rate, and says which errors are worth retrying, but there's no Retry-After or backoff guidance (10 of 15). The pricing page names a Premium SLA for Enterprise and claims 99.99 per cent uptime, with no SLA terms published (0). GA (10). 0+5+15+10+0+10 = 40.",
          "b": "No status page found on xcrawl.com or docs.xcrawl.com (0 of 20) and no readable incident history (5 of 30). No rate limits with numbers. The pricing page says only that Scale plans get higher rate limits (0 of 15). No 429 or overload guidance in the docs. The Python SDK retries 500, 502, 503 and 504 with backoff, but not 429 (0 of 15). The terms mention a Service Level Agreement \"if applicable\", and none is published (0 of 10). The API is sold publicly with no beta label (10). Total 15."
        },
        "scores": {
          "a": 40,
          "b": 15
        }
      },
      {
        "by": 20,
        "category": "ergonomics",
        "leads": "bright-data",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "Since MCP 3.1.0 (15 October 2026) all 32 tools are on by default, with `groups=` and `tools=` on the hosted URL or GROUPS and TOOLS locally to narrow them (5 for more than 30, plus 10 for the filters, 15). Markdown, text, HTML or JSON-LD output from the scrape tools, content cut at 200,000 characters, batch tools of up to 5 searches or 5 URLs and filterable dataset search, but no general field selection (15 of 20). Error codes with a retry-or-fix classification, and since 4.3.0 the local server uses the hosted server's codes (`rate_limited`, `invalid_input`, `quota_exceeded`) (17 of 20). Since 4.1.0 every tool sets readOnlyHint, destructiveHint and openWorldHint, with browser click and type marked destructive. Billing counts successful requests, and there are no idempotency keys (17 of 20, as firecrawl-mcp and apify-mcp). One required secret and auto-created zones, and official Python (`brightdata-sdk`) and JavaScript SDKs in the docs index (15). 15+15+17+17+15 = 79.",
          "b": "7 MCP tools per the Claude Code guide, compact by name and description, though the definitions themselves couldn't be read (22 of 25). Output formats, only_main_content, a search limit of 1 to 100, and crawl limit, depth and include or exclude regex keep responses sized (16 of 20). The SDKs raise errors with a code, status and request_id, but the docs list no error codes or recovery steps (5 of 20). Async jobs return IDs for polling and webhooks, with no idempotency keys or MCP annotations found (3 of 20). Only url or query is required, and Python and Node.js SDKs exist, but skip_tls_verification defaults to true (13 of 15). Total 59."
        },
        "scores": {
          "a": 79,
          "b": 59
        }
      }
    ],
    "facts": [
      {
        "a": "HTTP API",
        "b": "HTTP API",
        "name": "Kind"
      },
      {
        "a": "Bright Data",
        "b": "XCrawl",
        "name": "Vendor"
      },
      {
        "a": "https://api.brightdata.com/request",
        "b": "https://mcp.xcrawl.com/{YOUR_API_KEY}/mcp",
        "name": "Hosted endpoint"
      },
      {
        "a": "HTTP, Streamable HTTP",
        "b": "Streamable HTTP, stdio",
        "name": "Transports"
      },
      {
        "a": "OAuth or key",
        "b": "API key",
        "name": "Auth"
      },
      {
        "a": "Freemium",
        "b": "Freemium",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "32",
        "b": "7",
        "name": "Tools exposed"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "no",
        "name": "llms.txt"
      },
      {
        "a": "io.github.brightdata/brightdata-mcp",
        "b": "not listed",
        "name": "MCP registry"
      },
      {
        "a": "2026-11-02",
        "b": "2026-04-13",
        "name": "Last release"
      },
      {
        "a": "2026-06-16",
        "b": "no date given",
        "name": "Terms last updated"
      },
      {
        "a": "2026-05-14",
        "b": "no date given",
        "name": "Privacy policy last updated"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Customer content may train models"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Terms restrict automated access"
      },
      {
        "a": "yes",
        "b": "not found in the text",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "yes",
        "b": "not found in the text",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "2.6k stars",
        "b": "none",
        "name": "Popularity"
      },
      {
        "a": "4/5 (2)",
        "b": "none",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "Bright Data scores 59.4 (C) on agent readiness against XCrawl's 30.4 (F), and leads in every scored category.",
        "question": "Which is better for AI agents, Bright Data or XCrawl?"
      },
      {
        "answer": "Bright Data takes an API key or an OAuth sign-in. XCrawl needs an API key.",
        "question": "Do Bright Data and XCrawl need an API key?"
      },
      {
        "answer": "Yes. Bright Data has a hosted endpoint at https://api.brightdata.com/request and XCrawl at https://mcp.xcrawl.com/{YOUR_API_KEY}/mcp.",
        "question": "Can an agent call Bright Data and XCrawl without installing anything?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 40 against 15",
          "Schema \u0026 documentation, 74 against 35",
          "Agent ergonomics, 79 against 59",
          "Security \u0026 auth, 69 against 18",
          "Payments \u0026 pricing, 60 against 30",
          "Maintenance \u0026 community, 87 against 17",
          "Transparency \u0026 trust, 61 against 43"
        ],
        "also": null,
        "goodFor": "Hard targets and site-specific structured data (Amazon, LinkedIn, Instagram, Google Maps) at volume.",
        "slug": "bright-data",
        "watchFor": "No public status page or incident history"
      },
      {
        "aheadOn": null,
        "also": [
          "Runs on your own machine",
          "No incidents deducted, where Bright Data loses 6 points for them"
        ],
        "goodFor": "A general scrape, crawl, map and SERP API for agents, with 35 site-specific data endpoints.",
        "slug": "xcrawl",
        "watchFor": "Xcrawl LLC is named with no state, registration number or address, and the terms name no governing law"
      }
    ],
    "history": {
      "bright-data": [
        {
          "causes": [
            "method"
          ],
          "date": "2026-11-13",
          "delta": 2.5,
          "from": 56.9,
          "fromGrade": "C",
          "to": 59.4,
          "toGrade": "C"
        },
        {
          "causes": [
            "product",
            "evidence",
            "event"
          ],
          "date": "2026-11-04",
          "delta": -3.1,
          "from": 60,
          "fromGrade": "C",
          "to": 56.9,
          "toGrade": "C"
        },
        {
          "causes": [
            "evidence"
          ],
          "date": "2026-10-27",
          "delta": 0.2,
          "from": 59.8,
          "fromGrade": "C",
          "to": 60,
          "toGrade": "C"
        }
      ],
      "xcrawl": null
    },
    "job": {
      "capability": "web.scrape",
      "name": "Scraping"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-browseract.json",
        "title": "Bright Data vs BrowserAct",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-browseract"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-context-dev.json",
        "title": "Bright Data vs Context.dev",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-context-dev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-crawl4ai.json",
        "title": "Bright Data vs Crawl4AI",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-crawl4ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-crw.json",
        "title": "Bright Data vs fastCRW",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-crw"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-decodo.json",
        "title": "Bright Data vs Decodo Web Data API",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-decodo"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-diffbot.json",
        "title": "Bright Data vs Diffbot",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-diffbot"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-jevcrawl.json",
        "title": "Bright Data vs jevcrawl",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-jevcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-jina-reader.json",
        "title": "Bright Data vs Jina Reader",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-jina-reader"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-microlink.json",
        "title": "Bright Data vs Microlink",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-microlink"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-olostep.json",
        "title": "Bright Data vs Olostep",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-olostep"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-outcrawl.json",
        "title": "Bright Data vs Outcrawl",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-outcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-oxylabs-web-scraper.json",
        "title": "Bright Data vs Oxylabs Web Scraper API",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-oxylabs-web-scraper"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-scrape-do.json",
        "title": "Bright Data vs Scrape.do",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-scrape-do"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-scrapegraphai.json",
        "title": "Bright Data vs ScrapeGraphAI",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-scrapegraphai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-scrapeless.json",
        "title": "Bright Data vs Scrapeless",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-scrapeless"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-scrapeops.json",
        "title": "Bright Data vs ScrapeOps Proxy API Aggregator",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-scrapeops"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-scraperapi.json",
        "title": "Bright Data vs ScraperAPI",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-scraperapi"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-scrapewise.json",
        "title": "Bright Data vs Scrapewise",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-scrapewise"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-scrapfly.json",
        "title": "Bright Data vs Scrapfly",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-scrapfly"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-scrapingant.json",
        "title": "Bright Data vs ScrapingAnt",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-scrapingant"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-scrapingbee.json",
        "title": "Bright Data vs ScrapingBee",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-scrapingbee"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-scrapingdog.json",
        "title": "Bright Data vs Scrapingdog",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-scrapingdog"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-scrapling.json",
        "title": "Bright Data vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-spider-cloud.json",
        "title": "Bright Data vs Spider",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-spider-cloud"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-webscraping-ai.json",
        "title": "Bright Data vs WebScraping.AI",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-webscraping-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-zenrows.json",
        "title": "Bright Data vs ZenRows",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-zenrows"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-zyte.json",
        "title": "Bright Data vs Zyte API",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-zyte"
      },
      {
        "json": "https://www.anchorterminal.com/compare/browseract-vs-xcrawl.json",
        "title": "BrowserAct vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/browseract-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/context-dev-vs-xcrawl.json",
        "title": "Context.dev vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/context-dev-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crawl4ai-vs-xcrawl.json",
        "title": "Crawl4AI vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/crawl4ai-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crw-vs-xcrawl.json",
        "title": "fastCRW vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/crw-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/decodo-vs-xcrawl.json",
        "title": "Decodo Web Data API vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/decodo-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/jina-reader-vs-xcrawl.json",
        "title": "Jina Reader vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/jina-reader-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/microlink-vs-xcrawl.json",
        "title": "Microlink vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/microlink-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/olostep-vs-xcrawl.json",
        "title": "Olostep vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/olostep-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/outcrawl-vs-xcrawl.json",
        "title": "Outcrawl vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/outcrawl-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/oxylabs-web-scraper-vs-xcrawl.json",
        "title": "Oxylabs Web Scraper API vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/oxylabs-web-scraper-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrape-do-vs-xcrawl.json",
        "title": "Scrape.do vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/scrape-do-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapegraphai-vs-xcrawl.json",
        "title": "ScrapeGraphAI vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/scrapegraphai-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapeless-vs-xcrawl.json",
        "title": "Scrapeless vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/scrapeless-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scraperapi-vs-xcrawl.json",
        "title": "ScraperAPI vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/scraperapi-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapewise-vs-xcrawl.json",
        "title": "Scrapewise vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/scrapewise-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapfly-vs-xcrawl.json",
        "title": "Scrapfly vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/scrapfly-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapingant-vs-xcrawl.json",
        "title": "ScrapingAnt vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/scrapingant-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapingbee-vs-xcrawl.json",
        "title": "ScrapingBee vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/scrapingbee-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapingdog-vs-xcrawl.json",
        "title": "Scrapingdog vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/scrapingdog-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapling-vs-xcrawl.json",
        "title": "Scrapling vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/scrapling-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/spider-cloud-vs-xcrawl.json",
        "title": "Spider vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/spider-cloud-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/webscraping-ai-vs-xcrawl.json",
        "title": "WebScraping.AI vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/webscraping-ai-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/xcrawl-vs-zenrows.json",
        "title": "XCrawl vs ZenRows",
        "url": "https://www.anchorterminal.com/compare/xcrawl-vs-zenrows"
      },
      {
        "json": "https://www.anchorterminal.com/compare/xcrawl-vs-zyte.json",
        "title": "XCrawl vs Zyte API",
        "url": "https://www.anchorterminal.com/compare/xcrawl-vs-zyte"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-firecrawl-mcp.json",
        "title": "Bright Data vs Firecrawl MCP",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-firecrawl-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-qovia.json",
        "title": "Bright Data vs Qovia",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-qovia"
      },
      {
        "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-xcrawl.json",
        "title": "Firecrawl MCP vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-xcrawl.json",
        "title": "Diffbot vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-xcrawl.json",
        "title": "Nexscope vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/qovia-vs-xcrawl.json",
        "title": "Qovia vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/qovia-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapeatlas-vs-xcrawl.json",
        "title": "ScrapeAtlas vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/scrapeatlas-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/soldfetch-vs-xcrawl.json",
        "title": "SoldFetch vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/soldfetch-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-bright-data.json",
        "title": "Apify MCP Server vs Bright Data",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-bright-data"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-xcrawl.json",
        "title": "Apify MCP Server vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/jevcrawl-vs-xcrawl.json",
        "title": "jevcrawl vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/jevcrawl-vs-xcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapeops-vs-xcrawl.json",
        "title": "ScrapeOps Proxy API Aggregator vs XCrawl",
        "url": "https://www.anchorterminal.com/compare/scrapeops-vs-xcrawl"
      }
    ],
    "panel": null,
    "scores": [
      {
        "bright-data": 40,
        "by": 25,
        "edge": "bright-data",
        "key": "reliability",
        "name": "Reliability",
        "weight": 16,
        "xcrawl": 15
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "bright-data": 74,
        "by": 39,
        "edge": "bright-data",
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "weight": 13,
        "xcrawl": 35
      },
      {
        "bright-data": 79,
        "by": 20,
        "edge": "bright-data",
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "weight": 13,
        "xcrawl": 59
      },
      {
        "bright-data": 69,
        "by": 51,
        "edge": "bright-data",
        "key": "security",
        "name": "Security \u0026 auth",
        "weight": 14,
        "xcrawl": 18
      },
      {
        "bright-data": 60,
        "by": 30,
        "edge": "bright-data",
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "weight": 10,
        "xcrawl": 30
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "bright-data": 87,
        "by": 70,
        "edge": "bright-data",
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "weight": 7,
        "xcrawl": 17
      },
      {
        "bright-data": 61,
        "by": 18,
        "edge": "bright-data",
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "weight": 7,
        "xcrawl": 43
      }
    ],
    "summary": "Bright Data scores 59.4 (C) on agent readiness against XCrawl's 30.4 (F), and leads in every scored category. Both do scraping.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "bright-data": "Bright Data bills only successful requests, $1.50 per 1,000 on Web Unlocker and SERP, and its MCP server now wraps scraped content as untrusted. There's no public status page or incident history, and MCP 4.2.0 and 4.3.0 changed tool inputs and outputs in minor releases without notice.",
      "xcrawl": "A scrape, search, map and crawl API with 7 MCP tools, MIT Python and Node.js SDKs and 1,000 free credits without a card. Xcrawl LLC gives no address or registration. There is no OpenAPI spec, status page, rate limit, error reference or changelog, plan prices did not render for us, and the hosted MCP key travels in the URL."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/bright-data-vs-xcrawl",
    "json": "https://www.anchorterminal.com/compare/bright-data-vs-xcrawl.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/bright-data-vs-xcrawl.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/bright-data-vs-xcrawl.min.md"
  },
  "markdown": "Bright Data scores 59.4 (C) on agent readiness against XCrawl's 30.4 (F), and leads in every scored category. Both do scraping.\n\n- Bright Data: grade C, 59.4/100, rank #816 of 1563. Markdown https://www.anchorterminal.com/tools/bright-data.md · JSON https://www.anchorterminal.com/api/v1/tools/bright-data.json\n- XCrawl: grade F, 30.4/100, rank #1463 of 1563. Markdown https://www.anchorterminal.com/tools/xcrawl.md · JSON https://www.anchorterminal.com/api/v1/tools/xcrawl.json\n- Best web scraping and crawling APIs for AI agents: https://www.anchorterminal.com/best/web-scrapers/index.md\n- All 601 scrapers comparisons: https://www.anchorterminal.com/compare/web-scrapers/index.md\n\n## Which one, for what\n\n### Bright Data (C)\n\nGood for: Hard targets and site-specific structured data (Amazon, LinkedIn, Instagram, Google Maps) at volume.\n\nAhead on:\n- Reliability, 40 against 15\n- Schema \u0026 documentation, 74 against 35\n- Agent ergonomics, 79 against 59\n- Security \u0026 auth, 69 against 18\n- Payments \u0026 pricing, 60 against 30\n- Maintenance \u0026 community, 87 against 17\n- Transparency \u0026 trust, 61 against 43\n\nWatch for: No public status page or incident history\n\n### XCrawl (F)\n\nGood for: A general scrape, crawl, map and SERP API for agents, with 35 site-specific data endpoints.\n\nAlso in its favour:\n- Runs on your own machine\n- No incidents deducted, where Bright Data loses 6 points for them\n\nWatch for: Xcrawl LLC is named with no state, registration number or address, and the terms name no governing law\n\n\n## Why the edge\n\n### Maintenance \u0026 community: Bright Data +70\n\n- Bright Data (87): MCP v4.3.0 on 2 November 2026 (30). Ten MCP releases since 6 August, 2.11.2 (11 September), 2.11.3 (15 September), 2.12.0 (8 October), 3.0.0 (11 October), 3.1.0 (15 October), 4.0.0 (18 October), 4.1.0 (20 October), 4.1.1 (29 October), 4.2.0 (1 November) and 4.3.0, and product release notes dated 19, 24 and 27 October (20). Issues not read (GitHub's pages refuse our reader); outside pull requests such as #200 were merged within a week, and the 1 October count of 13 open issues stands (12 of 25). io.github.brightdata/brightdata-mcp in the official registry under a GitHub-verified namespace, now at 4.3.0, the latest release (15). Tests run in CI on every push, and the release workflow runs the tests and `npm audit signatures` before publishing with provenance (10). 30+20+12+15+10 = 87.\n- XCrawl (17): The newest dated releases are the Python SDK 1.1.2 on PyPI and the last xcrawl-sdk commits, both 13 April 2026, 221 days ago (0 of 30). Nothing dated in the 90 days from 22 August 2026 (0 of 20). We couldn't read GitHub issues. There is no public changelog, and support is by email, Telegram, WhatsApp and Microsoft Teams, with a 24-hour reply promised in the footer (5 of 15). Official Python and Node.js SDKs, unchanged for seven months (10 of 15). The SDK repository has 3 commits, no tests and no CI. Dependencies are current (2 of 10). Total 17.\n\n### Security \u0026 auth: Bright Data +51\n\n- Bright Data (69): API keys carry one of five roles (Admin, Finance, Ops, Limit, User), can be given an expiry, and are revoked or refreshed in the control panel, and the hosted MCP also takes OAuth 2.1 with PKCE and one `mcp` scope (30). The README's default hosted setup still puts the key in the URL as `?token=`, a documented option, so less 10 (20). User-role keys can't change configuration, tools load by group, and tools carry readOnlyHint and destructiveHint, but browser tools can fill forms and click with no confirmation step from the server (14 of 20). Since 3.1.0 results from search, scrape, scraper, dataset and browser tools are wrapped as untrusted web content with a per-call marker, and since 2.12.0 a content gate, documented in the README and on by default, asks the user through MCP elicitation before returning page text that looks like instructions to change the MCP configuration (12 of 15). The MCP `session_stats` tool reports calls in a session. We didn't find a per-request log for operators (5 of 15). ISO 27001, 27017 and 27018, SOC 2 Type II under NDA, a public SOC 3, a managed private bug bounty and security fixes in the MCP changelog per the 1 October check. No security.txt (404 on 4 November). OSV holds no advisory for @brightdata/mcp (18 of 20). 20+14+12+5+18 = 69.\n- XCrawl (18): A plain bearer API key from the dashboard with no scopes, and the MCP guide says to reissue an invalid key there (20). The recommended hosted MCP setup puts the key in the URL path, so less 10, read the way the checklist reads a key in a query string (10 of 30). The API only reads third-party pages and has no destructive account actions, but there is no read-only or least-privilege key (5 of 20). No prompt-injection guidance in the docs or the skills (0 of 15). Each response reports credits used, and xcrawl_key_status gives the balance, with no request log found (3 of 15). No security.txt, disclosure policy or bug bounty. The ISO 27001 badge on the home page links to no certificate or security page (0 of 20). Total 18.\n\n### Schema \u0026 documentation: Bright Data +39\n\n- Bright Data (74): No OpenAPI file found for the API. The MCP server has zod schemas on every tool, so partial credit (15 of 25). llms.txt at docs.brightdata.com with Markdown pages (10). MCP descriptions say what each tool returns, and the dataset tools say when to use them instead of `run_scraper` (14 of 20). Typed inputs with enums such as engine (bing or google), time_range and format (12 of 15). Per-product error catalogues for Web Unlocker, Browser API and scrapers, and curl examples (13 of 15). Release notes, now dated to 27 October 2026, and an MCP CHANGELOG with a gap between 2.6.0 and 2.10.0, per the 1 October reading (10 of 15).\n- XCrawl (35): No OpenAPI or other machine-readable spec found, and the MCP package is closed source, so its tool schemas couldn't be read (0 of 25). llms.txt returns 404. The docs have \"Copy page\" buttons, and the xcrawl-skills repository has Markdown skill files for agents (5 of 10). Each API reference page states what the endpoint does, with no guidance on when not to use it (8 of 20). Parameter tables give types, required flags, defaults and enums for formats, device and wait_until. cookies and headers are free maps (11 of 15). Request and response examples on every reference page, but no error responses or codes documented outside the MCP troubleshooting table (6 of 15). Versioned /v1 paths and no changelog (5 of 15). Total 35.\n\n### Payments \u0026 pricing: Bright Data +30\n\n- Bright Data (60): No x402, MPP or L402. Issue #126 asks for x402 and is open (0). Web Unlocker and SERP at $1.50 per 1,000 successful requests, $1.30 on Scale, published without a login (20). 5,000 requests a month, 'No credit card required' (20). A person has to sign up and create a key in the control panel (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.\n- XCrawl (30): No x402, MPP or L402 (0). The pricing page's plan table and credit table did not appear in the served page, and the docs give credit costs only in examples (1 for a plain scrape, 2 for a search), so pricing is scored absent (0 of 30, unchecked). 1,000 free credits on signup with no card (30). A person signs up in a browser at dash.xcrawl.com to get a key (0). Total 30.\n\n### Reliability: Bright Data +25\n\n- Bright Data (40): No public status page found. status.brightdata.com doesn't resolve and the docs index and security overview link none (0). No readable incident history, so 5 by the rubric (5). The SERP API fair-use page gives 1,000 requests a minute for unfunded accounts with HTTP 429 above it and a header that reads the account's limit, paid Web Unlocker plans state unlimited concurrency, and the free tier is 5,000 requests a month (15). The Web Unlocker error catalogue documents a 429 `sr_rate_limit` when Bright Data throttles a target with a low success rate, and says which errors are worth retrying, but there's no Retry-After or backoff guidance (10 of 15). The pricing page names a Premium SLA for Enterprise and claims 99.99 per cent uptime, with no SLA terms published (0). GA (10). 0+5+15+10+0+10 = 40.\n- XCrawl (15): No status page found on xcrawl.com or docs.xcrawl.com (0 of 20) and no readable incident history (5 of 30). No rate limits with numbers. The pricing page says only that Scale plans get higher rate limits (0 of 15). No 429 or overload guidance in the docs. The Python SDK retries 500, 502, 503 and 504 with backoff, but not 429 (0 of 15). The terms mention a Service Level Agreement \"if applicable\", and none is published (0 of 10). The API is sold publicly with no beta label (10). Total 15.\n\n### Agent ergonomics: Bright Data +20\n\n- Bright Data (79): Since MCP 3.1.0 (15 October 2026) all 32 tools are on by default, with `groups=` and `tools=` on the hosted URL or GROUPS and TOOLS locally to narrow them (5 for more than 30, plus 10 for the filters, 15). Markdown, text, HTML or JSON-LD output from the scrape tools, content cut at 200,000 characters, batch tools of up to 5 searches or 5 URLs and filterable dataset search, but no general field selection (15 of 20). Error codes with a retry-or-fix classification, and since 4.3.0 the local server uses the hosted server's codes (`rate_limited`, `invalid_input`, `quota_exceeded`) (17 of 20). Since 4.1.0 every tool sets readOnlyHint, destructiveHint and openWorldHint, with browser click and type marked destructive. Billing counts successful requests, and there are no idempotency keys (17 of 20, as firecrawl-mcp and apify-mcp). One required secret and auto-created zones, and official Python (`brightdata-sdk`) and JavaScript SDKs in the docs index (15). 15+15+17+17+15 = 79.\n- XCrawl (59): 7 MCP tools per the Claude Code guide, compact by name and description, though the definitions themselves couldn't be read (22 of 25). Output formats, only_main_content, a search limit of 1 to 100, and crawl limit, depth and include or exclude regex keep responses sized (16 of 20). The SDKs raise errors with a code, status and request_id, but the docs list no error codes or recovery steps (5 of 20). Async jobs return IDs for polling and webhooks, with no idempotency keys or MCP annotations found (3 of 20). Only url or query is required, and Python and Node.js SDKs exist, but skip_tls_verification defaults to true (13 of 15). Total 59.\n\n## Score by category\n\n| Category | Weight | Bright Data | XCrawl | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 40 | 15 | Bright Data +25 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 74 | 35 | Bright Data +39 |\n| Agent ergonomics | 13% | 79 | 59 | Bright Data +20 |\n| Security \u0026 auth | 14% | 69 | 18 | Bright Data +51 |\n| Payments \u0026 pricing | 10% | 60 | 30 | Bright Data +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 87 | 17 | Bright Data +70 |\n| Transparency \u0026 trust | 7% | 61 | 43 | Bright Data +18 |\n| Negative events | ≤15 | -6 | 0 | |\n| **Total** | | **59.4 · C** | **30.4 · F** | |\n\n## Facts side by side\n\n| Fact | Bright Data | XCrawl |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Bright Data | XCrawl |\n| Hosted endpoint | `https://api.brightdata.com/request` | `https://mcp.xcrawl.com/{YOUR_API_KEY}/mcp` |\n| Transports | HTTP, Streamable HTTP | Streamable HTTP, stdio |\n| Auth | OAuth or key | API key |\n| Pricing | Freemium | Freemium |\n| x402 | no | no |\n| Tools exposed | 32 | 7 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| MCP registry | `io.github.brightdata/brightdata-mcp` | not listed |\n| Last release | 2026-11-02 | 2026-04-13 |\n| Terms last updated | 2026-06-16 | no date given |\n| Privacy policy last updated | 2026-05-14 | no date given |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | yes | not found in the text |\n| Terms or service can change without notice | yes | yes |\n| Arbitration or class-action waiver | yes | not found in the text |\n| Popularity | 2.6k stars | none |\n| Agent reviews | 4/5 (2) | none |\n\n## How the scores have moved\n\n### Bright Data\n\n- +2.5 on 13 November 2026: checklist\n- -3.1 on 4 November 2026: product, new evidence, negative event\n- +0.2 on 27 October 2026: new evidence\n\n### XCrawl\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Bright Data.** Bright Data bills only successful requests, $1.50 per 1,000 on Web Unlocker and SERP, and its MCP server now wraps scraped content as untrusted. There's no public status page or incident history, and MCP 4.2.0 and 4.3.0 changed tool inputs and outputs in minor releases without notice.\n\n**XCrawl.** A scrape, search, map and crawl API with 7 MCP tools, MIT Python and Node.js SDKs and 1,000 free credits without a card. Xcrawl LLC gives no address or registration. There is no OpenAPI spec, status page, rate limit, error reference or changelog, plan prices did not render for us, and the hosted MCP key travels in the URL.\n\n## Before you call either\n\n### Bright Data\n\n1. Connect with OAuth or keep the `?token=` URL out of logs and shared configs\n2. Set `groups=` or `tools=` on the MCP URL to load only the tools you need. With neither, all 32 load\n3. Send `country` and `page` to the search tools from 4.3.0. `geo_location` and `cursor` now return `invalid_input`\n4. Expect JSON with a `content` field from `scrape_as_markdown` since 4.2.0, and use the browser tools for pages that need JavaScript\n5. Back off on a 429 `sr_rate_limit` or `rate_limited`. Bright Data throttles a target whose success rate drops\n\n### XCrawl\n\n1. Use the `npx xcrawl-mcp` setup with `XCRAWL_API_KEY` in the environment rather than the hosted URL, which puts the key in the path\n2. Set `skip_tls_verification` to false when the page's certificate matters, because scrape and crawl default it to true\n3. Set `crawler.limit` and `max_depth` on every crawl, since the defaults are 100 pages and depth 3\n4. Call xcrawl_key_status before a large crawl, because the docs give no credit table to estimate the cost\n5. Treat scraped Markdown and JSON as untrusted page content, since the docs give no prompt-injection guidance\n\n## Questions\n\n### Which is better for AI agents, Bright Data or XCrawl?\n\nBright Data scores 59.4 (C) on agent readiness against XCrawl's 30.4 (F), and leads in every scored category.\n\n### Do Bright Data and XCrawl need an API key?\n\nBright Data takes an API key or an OAuth sign-in. XCrawl needs an API key.\n\n### Can an agent call Bright Data and XCrawl without installing anything?\n\nYes. Bright Data has a hosted endpoint at https://api.brightdata.com/request and XCrawl at https://mcp.xcrawl.com/{YOUR_API_KEY}/mcp.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/bright-data-vs-xcrawl.json, and with the fewest tokens: https://www.anchorterminal.com/compare/bright-data-vs-xcrawl.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"bright-data\", \"b\": \"xcrawl\"}`. From a terminal: `anchor compare bright-data xcrawl`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/bright-data.json and https://www.anchorterminal.com/api/v1/tools/xcrawl.json\n\n## Other comparisons with Bright Data or XCrawl\n\n- [Bright Data vs BrowserAct](https://www.anchorterminal.com/compare/bright-data-vs-browseract.md)\n- [Bright Data vs Context.dev](https://www.anchorterminal.com/compare/bright-data-vs-context-dev.md)\n- [Bright Data vs Crawl4AI](https://www.anchorterminal.com/compare/bright-data-vs-crawl4ai.md)\n- [Bright Data vs fastCRW](https://www.anchorterminal.com/compare/bright-data-vs-crw.md)\n- [Bright Data vs Decodo Web Data API](https://www.anchorterminal.com/compare/bright-data-vs-decodo.md)\n- [Bright Data vs Diffbot](https://www.anchorterminal.com/compare/bright-data-vs-diffbot.md)\n- [Bright Data vs jevcrawl](https://www.anchorterminal.com/compare/bright-data-vs-jevcrawl.md)\n- [Bright Data vs Jina Reader](https://www.anchorterminal.com/compare/bright-data-vs-jina-reader.md)\n- [Bright Data vs Microlink](https://www.anchorterminal.com/compare/bright-data-vs-microlink.md)\n- [Bright Data vs Olostep](https://www.anchorterminal.com/compare/bright-data-vs-olostep.md)\n- [Bright Data vs Outcrawl](https://www.anchorterminal.com/compare/bright-data-vs-outcrawl.md)\n- [Bright Data vs Oxylabs Web Scraper API](https://www.anchorterminal.com/compare/bright-data-vs-oxylabs-web-scraper.md)\n- [Bright Data vs Scrape.do](https://www.anchorterminal.com/compare/bright-data-vs-scrape-do.md)\n- [Bright Data vs ScrapeGraphAI](https://www.anchorterminal.com/compare/bright-data-vs-scrapegraphai.md)\n- [Bright Data vs Scrapeless](https://www.anchorterminal.com/compare/bright-data-vs-scrapeless.md)\n- [Bright Data vs ScrapeOps Proxy API Aggregator](https://www.anchorterminal.com/compare/bright-data-vs-scrapeops.md)\n- [Bright Data vs ScraperAPI](https://www.anchorterminal.com/compare/bright-data-vs-scraperapi.md)\n- [Bright Data vs Scrapewise](https://www.anchorterminal.com/compare/bright-data-vs-scrapewise.md)\n- [Bright Data vs Scrapfly](https://www.anchorterminal.com/compare/bright-data-vs-scrapfly.md)\n- [Bright Data vs ScrapingAnt](https://www.anchorterminal.com/compare/bright-data-vs-scrapingant.md)\n- [Bright Data vs ScrapingBee](https://www.anchorterminal.com/compare/bright-data-vs-scrapingbee.md)\n- [Bright Data vs Scrapingdog](https://www.anchorterminal.com/compare/bright-data-vs-scrapingdog.md)\n- [Bright Data vs Scrapling](https://www.anchorterminal.com/compare/bright-data-vs-scrapling.md)\n- [Bright Data vs Spider](https://www.anchorterminal.com/compare/bright-data-vs-spider-cloud.md)\n- [Bright Data vs WebScraping.AI](https://www.anchorterminal.com/compare/bright-data-vs-webscraping-ai.md)\n- [Bright Data vs ZenRows](https://www.anchorterminal.com/compare/bright-data-vs-zenrows.md)\n- [Bright Data vs Zyte API](https://www.anchorterminal.com/compare/bright-data-vs-zyte.md)\n- [BrowserAct vs XCrawl](https://www.anchorterminal.com/compare/browseract-vs-xcrawl.md)\n- [Context.dev vs XCrawl](https://www.anchorterminal.com/compare/context-dev-vs-xcrawl.md)\n- [Crawl4AI vs XCrawl](https://www.anchorterminal.com/compare/crawl4ai-vs-xcrawl.md)\n- [fastCRW vs XCrawl](https://www.anchorterminal.com/compare/crw-vs-xcrawl.md)\n- [Decodo Web Data API vs XCrawl](https://www.anchorterminal.com/compare/decodo-vs-xcrawl.md)\n- [Jina Reader vs XCrawl](https://www.anchorterminal.com/compare/jina-reader-vs-xcrawl.md)\n- [Microlink vs XCrawl](https://www.anchorterminal.com/compare/microlink-vs-xcrawl.md)\n- [Olostep vs XCrawl](https://www.anchorterminal.com/compare/olostep-vs-xcrawl.md)\n- [Outcrawl vs XCrawl](https://www.anchorterminal.com/compare/outcrawl-vs-xcrawl.md)\n- [Oxylabs Web Scraper API vs XCrawl](https://www.anchorterminal.com/compare/oxylabs-web-scraper-vs-xcrawl.md)\n- [Scrape.do vs XCrawl](https://www.anchorterminal.com/compare/scrape-do-vs-xcrawl.md)\n- [ScrapeGraphAI vs XCrawl](https://www.anchorterminal.com/compare/scrapegraphai-vs-xcrawl.md)\n- [Scrapeless vs XCrawl](https://www.anchorterminal.com/compare/scrapeless-vs-xcrawl.md)\n- [ScraperAPI vs XCrawl](https://www.anchorterminal.com/compare/scraperapi-vs-xcrawl.md)\n- [Scrapewise vs XCrawl](https://www.anchorterminal.com/compare/scrapewise-vs-xcrawl.md)\n- [Scrapfly vs XCrawl](https://www.anchorterminal.com/compare/scrapfly-vs-xcrawl.md)\n- [ScrapingAnt vs XCrawl](https://www.anchorterminal.com/compare/scrapingant-vs-xcrawl.md)\n- [ScrapingBee vs XCrawl](https://www.anchorterminal.com/compare/scrapingbee-vs-xcrawl.md)\n- [Scrapingdog vs XCrawl](https://www.anchorterminal.com/compare/scrapingdog-vs-xcrawl.md)\n- [Scrapling vs XCrawl](https://www.anchorterminal.com/compare/scrapling-vs-xcrawl.md)\n- [Spider vs XCrawl](https://www.anchorterminal.com/compare/spider-cloud-vs-xcrawl.md)\n- [WebScraping.AI vs XCrawl](https://www.anchorterminal.com/compare/webscraping-ai-vs-xcrawl.md)\n- [XCrawl vs ZenRows](https://www.anchorterminal.com/compare/xcrawl-vs-zenrows.md)\n- [XCrawl vs Zyte API](https://www.anchorterminal.com/compare/xcrawl-vs-zyte.md)\n- [Bright Data vs Firecrawl MCP](https://www.anchorterminal.com/compare/bright-data-vs-firecrawl-mcp.md)\n- [Bright Data vs Qovia](https://www.anchorterminal.com/compare/bright-data-vs-qovia.md)\n- [Firecrawl MCP vs XCrawl](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-xcrawl.md)\n- [Diffbot vs XCrawl](https://www.anchorterminal.com/compare/diffbot-vs-xcrawl.md)\n- [Nexscope vs XCrawl](https://www.anchorterminal.com/compare/nexscope-vs-xcrawl.md)\n- [Qovia vs XCrawl](https://www.anchorterminal.com/compare/qovia-vs-xcrawl.md)\n- [ScrapeAtlas vs XCrawl](https://www.anchorterminal.com/compare/scrapeatlas-vs-xcrawl.md)\n- [SoldFetch vs XCrawl](https://www.anchorterminal.com/compare/soldfetch-vs-xcrawl.md)\n- [Apify MCP Server vs Bright Data](https://www.anchorterminal.com/compare/apify-mcp-vs-bright-data.md)\n- [Apify MCP Server vs XCrawl](https://www.anchorterminal.com/compare/apify-mcp-vs-xcrawl.md)\n- [jevcrawl vs XCrawl](https://www.anchorterminal.com/compare/jevcrawl-vs-xcrawl.md)\n- [ScrapeOps Proxy API Aggregator vs XCrawl](https://www.anchorterminal.com/compare/scrapeops-vs-xcrawl.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-20",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "1.0",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "Bright Data vs XCrawl",
        "url": ""
      }
    ],
    "description": "Bright Data scores 59.4 (C) to XCrawl's 30.4 (F) for scraping. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Bright Data C 59.4",
      "XCrawl F 30.4",
      "scores"
    ],
    "h1": "Bright Data vs XCrawl",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/bright-data-vs-xcrawl",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Bright Data vs XCrawl for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-11-20",
    "url": "https://www.anchorterminal.com/compare/bright-data-vs-xcrawl"
  },
  "tokens": {
    "markdown": 5500,
    "slim": 1030
  },
  "version": 1
}
