{ "data": { "a": { "slug": "twitterapi-io-mcp", "name": "TwitterAPI.io MCP", "vendor": "Prism Digital, LLC", "vendorUrl": "https://twitterapi.io", "kind": "mcp", "category": "social-media", "summary": "TwitterAPI.io's MCP server has 12 read-only tools for X (Twitter) posts, users, followers, replies and trends, billed per result from prepaid credits. It's a third-party data service, not X's own API.", "url": "https://www.anchorterminal.com/tools/twitterapi-io-mcp", "markdownUrl": "https://www.anchorterminal.com/tools/twitterapi-io-mcp.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/twitterapi-io-mcp.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/twitterapi-io-mcp.json", "dns": "twitterapi-io-mcp.grade.anchorterminal.com", "transports": [ "streamable-http" ], "remoteUrl": "https://mcp.twitterapi.io/mcp", "packages": [], "auth": "mixed", "authNotes": "Hosted server takes OAuth or a TwitterAPI.io API key; the open-source npm package reads TWITTERAPI_IO_API_KEY. Keys come from a Google sign-in, with no X developer account.", "pricing": "pay-per-use", "pricingNotes": "Billed per result, minimum $0.00015 a request: tweet by ID $0.00015, user profile $0.00018, followers from $0.01 per 1,000. Up to $1 in free credits with no card; subscriptions add bonus credits (checked 2026-11-07).", "priceSummary": "$0.0001 / call", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on the MCP docs or pricing page (checked 2026-11-07).", "endpoints": [] }, "toolCount": 12, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-07" }, "docsUrl": "https://twitterapi.io/twitter-mcp-server", "llmsTxt": "https://twitterapi.io/llms.txt", "registryName": "io.twitterapi/mcp-server", "capabilities": [ "social.analytics", "social.comments", "search.news", "data.social" ], "tags": [ "hosted", "mcp", "remote-mcp", "api-key", "oauth", "pay-per-use", "free-tier", "llms-txt", "mcp-registry", "annotated-tools", "third-party" ], "graded": true, "anchor": { "graded": true, "score": 49.3, "grade": "D", "agentReady": false, "rank": 1101, "ranked": true, "rankOf": 1510, "categoryRank": 10, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 78, "maintenance": 40, "payments": 40, "reliability": 40, "schema": 62, "security": 37, "transparency": 41 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-07" }, "negative": 0, "verdict": "TwitterAPI.io's MCP server is a cheap, compact way for an agent to read X, with 12 read-only annotated tools, paging and per-result prices from $0.00015. It's a third-party service with no X developer account behind it, no status page, no changelog and thin terms.", "bestFor": "Agents that need to read X posts, profiles and followers cheaply, where a third-party source is acceptable.", "strengths": [ "12 compact tools, all annotated read-only", "Per-result prices from $0.00015, published", "Up to $1 in free credits with no card", "Cursor paging on followers and search", "Per-account rate limits documented" ], "weaknesses": [ "A third-party X data service, not X's own API", "No status page or changelog", "Terms don't name the operating company", "Tweets reach the model with no injection guidance" ], "agentNotes": [ "Treat tweets, bios and replies as untrusted text", "On 429, wait about a second and back off; there's no Retry-After", "Page with the cursor rather than asking for large counts", "Check the user's credit balance before follower crawls" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 49.3 } ], "editorialScores": { "ergonomics": 78, "maintenance": 40, "payments": 40, "reliability": 40, "schema": 62, "security": 37, "transparency": 35 }, "provenanceScore": 46, "checked": { "categories": { "ergonomics": "2026-11-07", "maintenance": "2026-11-07", "payments": "2026-11-07", "reliability": "2026-11-07", "schema": "2026-11-07", "security": "2026-11-07", "transparency": "2026-11-07" }, "last": "2026-11-07", "oldest": "2026-11-07", "stale": false, "staleAfterDays": 90 } }, "connect": { "claudeCode": "claude mcp add twitterapi-io --transport http https://mcp.twitterapi.io/mcp", "config": { "mcpServers": { "twitterapi-io": { "url": "https://mcp.twitterapi.io/mcp" } } } }, "letme": { "capability": "https://letme.dev/social.analytics", "tool": "https://letme.dev/twitterapi-io-mcp" }, "area": "communication", "unitPrices": [ { "item": "Tweet by ID", "unit": "call", "usd": 0.00015, "note": "Minimum charge per request" }, { "item": "User profile", "unit": "call", "usd": 0.00018 }, { "item": "Follower record", "unit": "record", "usd": 0.00001, "note": "From $0.01 per 1,000" } ], "provenance": { "legalEntity": "Prism Digital, LLC", "domain": "twitterapi.io", "domainRegistered": "", "domainNote": "Not looked up: RDAP isn't requested under the 1 November 2026 rules.", "endpointOnVendorDomain": true, "terms": "https://twitterapi.io/terms", "privacy": "https://twitterapi.io/privacy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-07", "notes": [ "The terms (September 2025) say Twitterapi.io without a legal entity; the footer names Prism Digital, LLC, 131 Continental Dr Suite 305, Newark, DE 19713." ], "score": 46 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/twitterapi-io-mcp.json", "live": { "slug": "twitterapi-io-mcp", "probe": { "target": "https://mcp.twitterapi.io/mcp", "method": "mcp-initialize", "lastAt": "2026-11-08T00:56:11.203515911Z", "lastOk": true, "lastStatus": 200, "lastMs": 56, "lastNote": "initialize answered", "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 82, "p95ms24h": 164, "samples24h": 63, "samples30d": 63, "days": [ { "date": "2026-11-07", "probes": 53, "ok": 53 }, { "date": "2026-11-08", "probes": 10, "ok": 10 } ] }, "updatedAt": "2026-11-08T00:56:11.203515911Z" } }, "answer": "X MCP scores 53.1 (D) on agent readiness against TwitterAPI.io MCP's 49.3 (D), and leads in 5 of 7 scored categories. TwitterAPI.io MCP leads on agent ergonomics and payments \u0026 pricing.", "b": { "slug": "x-mcp", "name": "X MCP", "vendor": "X Corp.", "vendorUrl": "https://docs.x.com/tools/mcp", "kind": "mcp", "category": "social-media", "summary": "X MCP is X Corp.'s hosted Model Context Protocol server for the X API at api.x.com/mcp. It lets a model search posts, look up users, manage bookmarks, read trends and news, and draft Articles.", "url": "https://www.anchorterminal.com/tools/x-mcp", "markdownUrl": "https://www.anchorterminal.com/tools/x-mcp.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/x-mcp.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/x-mcp.json", "dns": "x-mcp.grade.anchorterminal.com", "repo": "https://github.com/xdevplatform/xurl", "license": "Proprietary hosted server under the X Developer Agreement. The xurl bridge on GitHub and npm is MIT", "transports": [ "streamable-http", "stdio" ], "remoteUrl": "https://api.x.com/mcp", "packages": [ { "registry": "npm", "name": "@xdevplatform/xurl" } ], "auth": "mixed", "authNotes": "A person creates an app in the X Developer Portal, on the Pay-per-use package in Production. Reads work with the app-only Bearer token in an `Authorization` header sent straight to https://api.x.com/mcp. User-context tools (bookmarks, Articles, the current user) need OAuth 2.0 authorisation code with PKCE through the local `xurl mcp` bridge, which takes CLIENT_ID and CLIENT_SECRET, needs the redirect URI http://localhost:8080/callback registered, opens a browser once, then caches and refreshes tokens in ~/.xurl. No dynamic client registration. Self-serve, with no review step documented.", "pricing": "usage", "pricingNotes": "Pay-per-use credits bought in advance in the Developer Console, with no subscription and no free tier. Reads are charged per resource returned ($0.005 a post, $0.010 a user, $0.001 for the app owner's own data) and writes per request ($0.005 a bookmark, $0.010 a trends request). A one-time $20 credit needs a saved payment card. The MCP page doesn't say MCP calls are billed at these API rates, though it requires a Pay-per-use app (https://docs.x.com/x-api/getting-started/pricing.md).", "priceSummary": "$0.005 / call", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the MCP page, the pricing page, the docs index or the OpenAPI spec (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 1352, "npmWeekly": 6027, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://docs.x.com/tools/mcp", "llmsTxt": "https://docs.x.com/llms.txt", "openapi": "https://api.x.com/2/openapi.json", "capabilities": [ "social.analytics" ], "tags": [ "official", "hosted", "mcp", "oauth", "usage-priced", "prepaid", "card-required", "openapi", "llms-txt", "closed-source", "cli", "go" ], "lastRelease": "2026-09-29", "graded": true, "anchor": { "graded": true, "score": 53.1, "grade": "D", "agentReady": false, "rank": 967, "ranked": true, "rankOf": 1510, "categoryRank": 7, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 45, "maintenance": 70, "payments": 20, "reliability": 72, "schema": 65, "security": 40, "transparency": 59 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-04" }, "negative": 0, "verdict": "First-party access to full-archive post search, user lookup, trends and news, with OAuth 2.0 PKCE scopes and per-resource prices published without a login. Every user must create a paid X developer app, the tool list isn't published, and the documented tools don't create posts.", "bestFor": "Research and monitoring on X by an agent whose owner already has, or will pay for, an X developer app, such as searching the archive, reading timelines and mentions, and filing bookmarks.", "strengths": [ "Hosted by X on api.x.com, with full-archive post search, user search and news search among the documented tools", "OAuth 2.0 with PKCE (S256 in the xurl bridge) and automatic token refresh, with the token sent in a header", "Per-resource prices are public, such as $0.005 a post read and $0.001 for reads of the app owner's own data", "The xurl bridge is MIT, with CI that builds, tests and lints on every push to main", "llms.txt, Markdown for every docs page and a public OpenAPI spec (version 2.173, 200 paths)" ], "weaknesses": [ "No dynamic client registration, so each user creates an X developer app on the Pay-per-use package in Production", "The tool list and tool schemas aren't published, and neither public repository carries them", "The documented tools don't create posts, replies, likes or follows. Writes cover bookmarks and Articles", "xurl 1.3.4 asks for a fixed set of 24 scopes, including tweet.write and dm.write, with no flag to narrow them", "No guidance on prompt injection, though every post returned is text written by strangers", "The platform changelog has no entry for the hosted server, which publishes no version history" ], "agentNotes": [ "Use the app-only Bearer header for read-only work. Bookmarks, Articles and any tool working in the user's name need the xurl bridge", "Set the client's startup timeout to 300 seconds or more, because the bridge holds the handshake until the first browser login ends", "On a headless host run `xurl auth oauth2 --headless` first, with CLIENT_ID and CLIENT_SECRET exported in that shell", "On `client-not-enrolled`, move the app to Pay-per-use and Production in the developer portal", "On 429, wait until the Unix time in `x-rate-limit-reset`. No Retry-After header is documented" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 53.1 } ], "editorialScores": { "ergonomics": 45, "maintenance": 70, "payments": 20, "reliability": 72, "schema": 65, "security": 40, "transparency": 33 }, "provenanceScore": 85, "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": "2026-11-04", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm install -g @xdevplatform/xurl", "config": { "mcpServers": { "xapi": { "args": [ "-y", "@xdevplatform/xurl", "mcp", "https://api.x.com/mcp" ], "command": "npx", "env": { "CLIENT_ID": "YOUR_X_APP_CLIENT_ID", "CLIENT_SECRET": "YOUR_X_APP_CLIENT_SECRET" } } } } }, "letme": { "capability": "https://letme.dev/social.analytics", "tool": "https://letme.dev/x-mcp" }, "sameCompany": [ "x-ads" ], "area": "communication", "unitPrices": [ { "item": "Post read", "unit": "record", "usd": 0.005, "note": "per post returned, deduplicated within a UTC day" }, { "item": "User read", "unit": "record", "usd": 0.01, "note": "per user returned" }, { "item": "Owned read (the app owner's own posts, bookmarks, followers)", "unit": "record", "usd": 0.001, "note": "when the authenticated user owns the app" }, { "item": "Bookmark write", "unit": "call", "usd": 0.005, "note": "per request" }, { "item": "Trends request", "unit": "call", "usd": 0.01, "note": "per request" } ], "provenance": { "legalEntity": "X Corp.", "domain": "x.com", "domainRegistered": "1993-04-02", "endpointOnVendorDomain": true, "terms": "https://docs.x.com/developer-terms/agreement", "privacy": "https://x.com/en/privacy", "statusPage": "https://developer.x.com/status", "changelog": "https://docs.x.com/changelog", "securityTxt": "unknown", "checked": "2026-11-04", "notes": [ "The Developer Agreement (last updated 27 April 2026, re-read on 4 November) names X Corp. as the contracting party, or X Internet Unlimited Company for a developer in the EU, EFTA or the United Kingdom.", "The privacy link is x.com/en/privacy. x.com's robots.txt disallows every path for unnamed agents, so the policy and X's general terms of service are closed to us and their 8 October readings are struck.", "x.com/.well-known/security.txt is closed to us by robots.txt, so its 8 October reading (expired 1 January 2024) is struck. docs.x.com and developer.x.com returned 404 for the file on 4 November, and api.x.com's robots.txt disallows every path for unnamed agents.", "https://developer.x.com/status needs JavaScript and showed our reader no status data on 8 October. The incident history is at https://docs.x.com/incidents.md.", "RDAP for x.com gives a registration date of 1993-04-02." ], "score": 85 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/x-mcp.json", "live": { "slug": "x-mcp", "probe": { "target": "https://api.x.com/mcp", "method": "mcp-initialize", "lastAt": "2026-11-08T00:56:15.45648236Z", "lastOk": true, "lastStatus": 401, "lastMs": 200, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 138, "p95ms24h": 229, "samples24h": 244, "samples30d": 7529, "days": [ { "date": "2026-10-08", "probes": 93, "ok": 93 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 250, "ok": 250 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 243, "ok": 243 }, { "date": "2026-11-08", "probes": 10, "ok": 10 } ] }, "vendorStatus": { "page": "https://developer.x.com/status", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-08T00:32:38.223861776Z" }, "versions": [ { "registry": "github", "name": "xdevplatform/xurl", "version": "v1.3.4", "released": "2026-09-29", "seenAt": "2026-11-07T00:18:06.841117376Z" }, { "registry": "npm", "name": "@xdevplatform/xurl", "version": "1.3.4", "seenAt": "2026-11-07T00:18:06.410394603Z" } ], "githubStars": 1365, "npmWeekly": 4788, "securityTxt": { "url": "https://x.com/.well-known/security.txt", "state": "expired", "expires": "2024-01-01T06:00:00.000Z", "checkedAt": "2026-11-07T16:01:24.213831632Z" }, "llmsTxt": { "url": "https://docs.x.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:34:26.588701548Z" }, "domain": { "domain": "x.com", "registered": "1993-04-02", "source": "https://rdap.verisign.com/com/v1/domain/x.com", "checkedAt": "2026-11-01T14:25:10.648320067Z" }, "pages": [ { "url": "https://docs.x.com/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:19:48.52525792Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "d1064f68558e" }, { "url": "https://docs.x.com/x-api/getting-started/pricing.md", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:08:51.11758556Z", "changedAt": "2026-10-31T06:11:50.27229026Z", "fingerprint": "7318d8cce7ac" }, { "url": "https://x.com/en/privacy", "kind": "privacy", "status": 0, "checkedAt": "2026-11-07T14:38:09.200102329Z", "changedAt": "0001-01-01T00:00:00Z", "blockedByRobots": true }, { "url": "https://docs.x.com/developer-terms/agreement", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:19:50.776391045Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "69ecb268f31a" } ], "mcpTools": { "url": "https://api.x.com/mcp", "checkedAt": "2026-11-07T01:49:14.492812265Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-10-08T21:34:02.68340277Z" }, "github": { "repo": "xdevplatform/xurl", "checkedAt": "2026-11-02T09:39:32.883519302Z", "stars": 1364, "archived": false, "issuesEnabled": true, "pushedAt": "2026-09-29T21:20:24Z", "openIssues": 12, "openPRs": 11, "issuesOpened90d": 8, "issuesClosed90d": 0, "prsMerged90d": 4, "ci": { "branch": "main", "runs": 42, "success": 42, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-09-29T21:23:44Z" }, "replies": { "sampled": 25, "unanswered": 12, "medianDays": 34.9 } }, "updatedAt": "2026-11-08T00:56:15.45648236Z" } }, "edges": [ { "by": 33, "category": "ergonomics", "leads": "twitterapi-io-mcp", "name": "Agent ergonomics", "reasons": { "a": "12 compact tools, about 12 KB (15). Cursor-based paging on followers and search (18 of 20). 429 handling documented (10 of 20). All 12 annotated read-only (20). Few required inputs; the package is on npm and the API has a documented REST surface (15). 15 + 18 + 10 + 20 + 15 = 78.", "b": "Per the 8 October check, not re-read on 4 November, apart from the xurl clone and the MCP page. The number of tools isn't published. One docs page lists six groups and another says XMCP exposes 200+ endpoints as tools, so context cost is not established (5 of 25). The API has `max_results`, `pagination_token`, field selection and expansions. Whether each MCP tool passes them through is unread (12 of 20). Errors are problem+json with a type URI, title and detail, and the xurl CHANGELOG (1.2.0) says the bridge turns transport and token failures into JSON-RPC errors keyed to the request (15 of 20). No idempotency keys, and no readOnlyHint or destructiveHint documented. The bridge refreshes the token and retries after a 401 (4 of 20). One npx line starts the bridge and the URL has a default, but each user first creates an app, registers a redirect URI and sets a 300-second startup timeout. Official XDKs exist for Python and TypeScript (9 of 15). 5+12+15+4+9 = 45." }, "scores": { "a": 78, "b": 45 } }, { "by": 32, "category": "reliability", "leads": "x-mcp", "name": "Reliability", "reasons": { "a": "No status page found (0). No incident history (5). Per-account QPS limits documented by tier (15). 'Hitting the ceiling returns an HTTP 429 (no Retry-After header is sent). Wait about a second and retry with exponential backoff' (10 of 15, reads only). No SLA; the terms disclaim uninterrupted service (0). Not labelled beta (10). 0 + 5 + 15 + 10 + 0 + 10 = 40.", "b": "Read with the hosted lines, since the server runs at api.x.com and the bridge only relays. docs.x.com and developer.x.com are separate hosts with open robots.txt files. The incident history was re-read on 4 November, and the other lines are per the 8 October check, not re-read. A status page exists at developer.x.com/status but needs JavaScript and showed our reader nothing. The dated incident history at docs.x.com/incidents.md lists incidents by title, with no component view and no MCP entry (15 of 20, an earlier partial kept). On 4 November that history still has no incident dated after 1 July 2026, apart from a 'Missing entities.annotations' entry marked ongoing since 24 March 2026, so the earlier partial stays, as the x-ads listing holds it on the same page (25 of 30). API rate limits are published per endpoint, such as 300 per 15 minutes and 1 a second for full-archive search and 50 per 15 minutes for bookmark writes. The MCP page gives no numbers of its own and says only that writes are stricter than reads (12 of 15, an earlier partial kept). 429s come with `x-rate-limit-reset` and the docs advise waiting for it and backing off. No Retry-After and no idempotency keys or safe-retry guidance for writes were found, so backoff alone (10). No SLA found for Pay-per-use (0). The MCP page carries no beta or preview label (10). 15+25+12+10+0+10 = 72." }, "scores": { "a": 40, "b": 72 } }, { "by": 30, "category": "maintenance", "leads": "x-mcp", "name": "Maintenance \u0026 community", "reasons": { "a": "Registry entry io.twitterapi/mcp-server updated 6 November 2026 (30). No dated changelog (0). Support channel not checked (0 of 15). Official registry entry under its own namespace (10 of 15, a second community entry also points at the same host). No package health read (0). 30 + 0 + 0 + 10 + 0 = 40. Registry presence read from Anchor Terminal's own daily import of the official MCP registry (/api/v1/registry.json, 6 November 2026), not the registry's API.", "b": "X's platform changelog (re-read on 4 November) has an X API v2 entry dated 26 October 2026 (Direct Message refusal error details), 9 days before 4 November, and the xurl bridge's newest release is 1.3.4 on 29 September 2026 (30). In the 90 days from 6 August the changelog dates six X API v2 entries, on 1 September (documented media limits), 21 September (OAuth 1.0a to 2.0 token exchange), 29 September (broadcast chat removal events), 1 October (a rewritten guide), 2 October (free credit incentives) and 26 October. Ads API entries are left to the x-ads listing. xurl tagged 1.3.2 (24 September, a Homebrew cask fix, packaging-only, half), 1.3.3 (29 September, an `xurl chat add-members` fix, full) and 1.3.4 (29 September, republishing 1.3.3's binaries and npm package, packaging-only, half). Well over three dated entries (20). The xmcp repository has no tags and no commit since 9 April 2026. The xurl changelog credits fixes to numbered issues. Issue threads couldn't be read (GitHub's pages answer 403) and the developer forum's robots.txt closes it to us (12 of 25, an earlier partial kept). The registry line's readings on 8 October and 4 November both came from the official MCP registry's JSON search API, which this run doesn't use, so they are struck and no registry entry is established (0). Go 1.24 with build, test, gofmt and release-build jobs in CI, results unread (8 of 10). 30+20+12+0+8 = 70." }, "scores": { "a": 40, "b": 70 } }, { "by": 20, "category": "payments", "leads": "twitterapi-io-mcp", "name": "Payments \u0026 pricing", "reasons": { "a": "No machine payment protocol (0). Per-result prices public (20). Up to $1 in free credits, no card (20). A Google sign-in in a browser gets the key (0). 0 + 20 + 20 + 0 = 40.", "b": "Per the 8 October check, not re-read on 4 November. No x402, MPP or L402 (0). Per-resource and per-request prices are published without a login, such as $0.005 a post read, $0.010 a user read and $0.005 a bookmark write (20). No free tier. Credits are bought in advance, and the one-time $20 credit needs a saved payment card (0). A person signs in to the developer portal, creates an app and completes a browser login (0). 0+20+0+0 = 20." }, "scores": { "a": 40, "b": 20 } }, { "by": 18, "category": "transparency", "leads": "x-mcp", "name": "Transparency \u0026 trust", "reasons": { "a": "The MCP package is MIT on npm; the service is closed under terms from September 2025 that don't name the company, which appears in the footer as Prism Digital, LLC of Newark, Delaware (15). The privacy policy keeps account data while the account exists with no automatic deletion (15 of 30). No deprecation policy (0). Subprocessors not listed in the pages read (5 of 20). 15 + 15 + 0 + 5 = 35.", "b": "Editorial half only. The hosted server is closed, under a Developer Agreement last updated 27 April 2026, and the bridge is MIT per the xurl LICENSE read on 4 November (18 of 30, an earlier partial kept). The 8 October data-handling reading came from X's privacy policy and terms of service on x.com, whose robots.txt disallows every path for unnamed agents, so it is struck. The Developer Agreement (re-read on 4 November) links a controller-to-controller data protection addendum on gdpr.x.com, which wasn't read, and no retention statement or subprocessor list for developers was found in the pages still readable (0 of 30). The versioning page (re-read on 4 November) limits breaking changes to major versions, at most yearly, with migration guides, and says a deprecated version works for 'a defined period' without stating one. Dated notices exist but can be short, such as five days for the Account Activity replay endpoint in March 2026 and four days for the removal of follows, likes and quote posts from self-serve tiers in April 2026. Dated notices with no stated period take this run's settled 15 (15 of 20, from 14). The controller names came from the struck privacy policy, and no subprocessor or data location list was found (0 of 20). 18+0+15+0 = 33." }, "scores": { "a": 41, "b": 59 } } ], "facts": [ { "a": "MCP server", "b": "MCP server", "name": "Kind" }, { "a": "Prism Digital, LLC", "b": "X Corp.", "name": "Vendor" }, { "a": "https://mcp.twitterapi.io/mcp", "b": "https://api.x.com/mcp", "name": "Hosted endpoint" }, { "a": "Streamable HTTP", "b": "Streamable HTTP, stdio", "name": "Transports" }, { "a": "OAuth or key", "b": "OAuth or key", "name": "Auth" }, { "a": "pay-per-use", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "none", "b": "Proprietary hosted server under the X Developer Agreement. The xurl bridge on GitHub and npm is MIT", "name": "Licence" }, { "a": "12", "b": "none", "name": "Tools exposed" }, { "a": "yes", "b": "yes", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "io.twitterapi/mcp-server", "b": "not listed", "name": "MCP registry" }, { "a": "none", "b": "2026-09-29", "name": "Last release" }, { "a": "not read yet", "b": "2026-04-27", "name": "Terms last updated" }, { "a": "not read yet", "b": "couldn't be read", "name": "Privacy policy last updated" }, { "a": "not read yet", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not read yet", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not read yet", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "1.4k stars, 6k npm/wk", "name": "Popularity" } ], "faq": [ { "answer": "X MCP scores 53.1 (D) on agent readiness against TwitterAPI.io MCP's 49.3 (D), and leads in 5 of 7 scored categories. TwitterAPI.io MCP leads on agent ergonomics and payments \u0026 pricing.", "question": "Which is better for AI agents, TwitterAPI.io MCP or X MCP?" }, { "answer": "Both take an API key or an OAuth sign-in.", "question": "Do TwitterAPI.io MCP and X MCP need an API key?" }, { "answer": "Yes. TwitterAPI.io MCP has a hosted endpoint at https://mcp.twitterapi.io/mcp and X MCP at https://api.x.com/mcp.", "question": "Can an agent call TwitterAPI.io MCP and X MCP without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Agent ergonomics, 78 against 45", "Payments \u0026 pricing, 40 against 20" ], "also": null, "goodFor": "Agents that need to read X posts, profiles and followers cheaply, where a third-party source is acceptable.", "slug": "twitterapi-io-mcp", "watchFor": "A third-party X data service, not X's own API" }, { "aheadOn": [ "Reliability, 72 against 40", "Maintenance \u0026 community, 70 against 40", "Transparency \u0026 trust, 59 against 41" ], "also": [ "Runs on your own machine" ], "goodFor": "Research and monitoring on X by an agent whose owner already has, or will pay for, an X developer app, such as searching the archive, reading timelines and mentions, and filing bookmarks.", "slug": "x-mcp", "watchFor": "No dynamic client registration, so each user creates an X developer app on the Pay-per-use package in Production" } ], "history": { "twitterapi-io-mcp": null, "x-mcp": [ { "causes": [ "evidence" ], "date": "2026-11-04", "delta": -2.3, "from": 55.4, "fromGrade": "C", "to": 53.1, "toGrade": "D" } ] }, "job": { "capability": "social.analytics", "name": "Social analytics" }, "others": [ { "json": "https://www.anchorterminal.com/compare/ayrshare-vs-twitterapi-io-mcp.json", "title": "Ayrshare API + MCP vs TwitterAPI.io MCP", "url": "https://www.anchorterminal.com/compare/ayrshare-vs-twitterapi-io-mcp" }, { "json": "https://www.anchorterminal.com/compare/ayrshare-vs-x-mcp.json", "title": "Ayrshare API + MCP vs X MCP", "url": "https://www.anchorterminal.com/compare/ayrshare-vs-x-mcp" }, { "json": "https://www.anchorterminal.com/compare/blotato-vs-twitterapi-io-mcp.json", "title": "Blotato vs TwitterAPI.io MCP", "url": "https://www.anchorterminal.com/compare/blotato-vs-twitterapi-io-mcp" }, { "json": "https://www.anchorterminal.com/compare/blotato-vs-x-mcp.json", "title": "Blotato vs X MCP", "url": "https://www.anchorterminal.com/compare/blotato-vs-x-mcp" }, { "json": "https://www.anchorterminal.com/compare/buffer-vs-twitterapi-io-mcp.json", "title": "Buffer API + MCP vs TwitterAPI.io MCP", "url": "https://www.anchorterminal.com/compare/buffer-vs-twitterapi-io-mcp" }, { "json": "https://www.anchorterminal.com/compare/buffer-vs-x-mcp.json", "title": "Buffer API + MCP vs X MCP", "url": "https://www.anchorterminal.com/compare/buffer-vs-x-mcp" }, { "json": "https://www.anchorterminal.com/compare/bundle-social-vs-twitterapi-io-mcp.json", "title": "bundle.social vs TwitterAPI.io MCP", "url": "https://www.anchorterminal.com/compare/bundle-social-vs-twitterapi-io-mcp" }, { "json": "https://www.anchorterminal.com/compare/bundle-social-vs-x-mcp.json", "title": "bundle.social vs X MCP", "url": "https://www.anchorterminal.com/compare/bundle-social-vs-x-mcp" }, { "json": "https://www.anchorterminal.com/compare/late-vs-twitterapi-io-mcp.json", "title": "Zernio (formerly Late) API + MCP vs TwitterAPI.io MCP", "url": "https://www.anchorterminal.com/compare/late-vs-twitterapi-io-mcp" }, { "json": "https://www.anchorterminal.com/compare/late-vs-x-mcp.json", "title": "Zernio (formerly Late) API + MCP vs X MCP", "url": "https://www.anchorterminal.com/compare/late-vs-x-mcp" }, { "json": "https://www.anchorterminal.com/compare/metricool-vs-twitterapi-io-mcp.json", "title": "Metricool API + MCP vs TwitterAPI.io MCP", "url": "https://www.anchorterminal.com/compare/metricool-vs-twitterapi-io-mcp" }, { "json": "https://www.anchorterminal.com/compare/metricool-vs-x-mcp.json", "title": "Metricool API + MCP vs X MCP", "url": "https://www.anchorterminal.com/compare/metricool-vs-x-mcp" }, { "json": "https://www.anchorterminal.com/compare/mixpost-vs-twitterapi-io-mcp.json", "title": "Mixpost API + MCP vs TwitterAPI.io MCP", "url": "https://www.anchorterminal.com/compare/mixpost-vs-twitterapi-io-mcp" }, { "json": "https://www.anchorterminal.com/compare/mixpost-vs-x-mcp.json", "title": "Mixpost API + MCP vs X MCP", "url": "https://www.anchorterminal.com/compare/mixpost-vs-x-mcp" }, { "json": "https://www.anchorterminal.com/compare/oneup-vs-twitterapi-io-mcp.json", "title": "OneUp API + MCP vs TwitterAPI.io MCP", "url": "https://www.anchorterminal.com/compare/oneup-vs-twitterapi-io-mcp" }, { "json": "https://www.anchorterminal.com/compare/oneup-vs-x-mcp.json", "title": "OneUp API + MCP vs X MCP", "url": "https://www.anchorterminal.com/compare/oneup-vs-x-mcp" }, { "json": "https://www.anchorterminal.com/compare/post-bridge-vs-twitterapi-io-mcp.json", "title": "Post Bridge API + MCP vs TwitterAPI.io MCP", "url": "https://www.anchorterminal.com/compare/post-bridge-vs-twitterapi-io-mcp" }, { "json": "https://www.anchorterminal.com/compare/post-bridge-vs-x-mcp.json", "title": "Post Bridge API + MCP vs X MCP", "url": "https://www.anchorterminal.com/compare/post-bridge-vs-x-mcp" }, { "json": "https://www.anchorterminal.com/compare/postiz-vs-twitterapi-io-mcp.json", "title": "Postiz API + MCP vs TwitterAPI.io MCP", "url": "https://www.anchorterminal.com/compare/postiz-vs-twitterapi-io-mcp" }, { "json": "https://www.anchorterminal.com/compare/postiz-vs-x-mcp.json", "title": "Postiz API + MCP vs X MCP", "url": "https://www.anchorterminal.com/compare/postiz-vs-x-mcp" }, { "json": "https://www.anchorterminal.com/compare/publer-vs-twitterapi-io-mcp.json", "title": "Publer API + MCP vs TwitterAPI.io MCP", "url": "https://www.anchorterminal.com/compare/publer-vs-twitterapi-io-mcp" }, { "json": "https://www.anchorterminal.com/compare/publer-vs-x-mcp.json", "title": "Publer API + MCP vs X MCP", "url": "https://www.anchorterminal.com/compare/publer-vs-x-mcp" }, { "json": "https://www.anchorterminal.com/compare/socialcannon-vs-twitterapi-io-mcp.json", "title": "SocialCannon vs TwitterAPI.io MCP", "url": "https://www.anchorterminal.com/compare/socialcannon-vs-twitterapi-io-mcp" }, { "json": "https://www.anchorterminal.com/compare/socialcannon-vs-x-mcp.json", "title": "SocialCannon vs X MCP", "url": "https://www.anchorterminal.com/compare/socialcannon-vs-x-mcp" }, { "json": "https://www.anchorterminal.com/compare/sprout-social-vs-twitterapi-io-mcp.json", "title": "Sprout Social API vs TwitterAPI.io MCP", "url": "https://www.anchorterminal.com/compare/sprout-social-vs-twitterapi-io-mcp" }, { "json": "https://www.anchorterminal.com/compare/sprout-social-vs-x-mcp.json", "title": "Sprout Social API vs X MCP", "url": "https://www.anchorterminal.com/compare/sprout-social-vs-x-mcp" }, { "json": "https://www.anchorterminal.com/compare/twitterapi-io-mcp-vs-upload-post.json", "title": "TwitterAPI.io MCP vs Upload-Post API + MCP", "url": "https://www.anchorterminal.com/compare/twitterapi-io-mcp-vs-upload-post" }, { "json": "https://www.anchorterminal.com/compare/twitterapi-io-mcp-vs-xpoz-mcp.json", "title": "TwitterAPI.io MCP vs Xpoz MCP", "url": "https://www.anchorterminal.com/compare/twitterapi-io-mcp-vs-xpoz-mcp" }, { "json": "https://www.anchorterminal.com/compare/upload-post-vs-x-mcp.json", "title": "Upload-Post API + MCP vs X MCP", "url": "https://www.anchorterminal.com/compare/upload-post-vs-x-mcp" }, { "json": "https://www.anchorterminal.com/compare/x-mcp-vs-xpoz-mcp.json", "title": "X MCP vs Xpoz MCP", "url": "https://www.anchorterminal.com/compare/x-mcp-vs-xpoz-mcp" } ], "panel": null, "scores": [ { "by": 32, "edge": "x-mcp", "key": "reliability", "name": "Reliability", "twitterapi-io-mcp": 40, "weight": 16, "x-mcp": 72 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 3, "edge": "x-mcp", "key": "schema", "name": "Schema \u0026 documentation", "twitterapi-io-mcp": 62, "weight": 13, "x-mcp": 65 }, { "by": 33, "edge": "twitterapi-io-mcp", "key": "ergonomics", "name": "Agent ergonomics", "twitterapi-io-mcp": 78, "weight": 13, "x-mcp": 45 }, { "by": 3, "edge": "x-mcp", "key": "security", "name": "Security \u0026 auth", "twitterapi-io-mcp": 37, "weight": 14, "x-mcp": 40 }, { "by": 20, "edge": "twitterapi-io-mcp", "key": "payments", "name": "Payments \u0026 pricing", "twitterapi-io-mcp": 40, "weight": 10, "x-mcp": 20 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 30, "edge": "x-mcp", "key": "maintenance", "name": "Maintenance \u0026 community", "twitterapi-io-mcp": 40, "weight": 7, "x-mcp": 70 }, { "by": 18, "edge": "x-mcp", "key": "transparency", "name": "Transparency \u0026 trust", "twitterapi-io-mcp": 41, "weight": 7, "x-mcp": 59 } ], "summary": "X MCP scores 53.1 (D) on agent readiness against TwitterAPI.io MCP's 49.3 (D), and leads in 5 of 7 scored categories. TwitterAPI.io MCP leads on agent ergonomics and payments \u0026 pricing. Both do social analytics.", "tasks": null, "tutorials": [ { "title": "Research product mentions with X MCP", "tool": "x-mcp", "url": "https://www.anchorterminal.com/tutorials/x-mcp/" } ], "verdicts": { "twitterapi-io-mcp": "TwitterAPI.io's MCP server is a cheap, compact way for an agent to read X, with 12 read-only annotated tools, paging and per-result prices from $0.00015. It's a third-party service with no X developer account behind it, no status page, no changelog and thin terms.", "x-mcp": "First-party access to full-archive post search, user lookup, trends and news, with OAuth 2.0 PKCE scopes and per-resource prices published without a login. Every user must create a paid X developer app, the tool list isn't published, and the documented tools don't create posts." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/twitterapi-io-mcp-vs-x-mcp", "json": "https://www.anchorterminal.com/compare/twitterapi-io-mcp-vs-x-mcp.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/twitterapi-io-mcp-vs-x-mcp.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/twitterapi-io-mcp-vs-x-mcp.min.md" }, "markdown": "X MCP scores 53.1 (D) on agent readiness against TwitterAPI.io MCP's 49.3 (D), and leads in 5 of 7 scored categories. TwitterAPI.io MCP leads on agent ergonomics and payments \u0026 pricing. Both do social analytics.\n\n- TwitterAPI.io MCP: grade D, 49.3/100, rank #1101 of 1510. Markdown https://www.anchorterminal.com/tools/twitterapi-io-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/twitterapi-io-mcp.json\n- X MCP: grade D, 53.1/100, rank #967 of 1510. Markdown https://www.anchorterminal.com/tools/x-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/x-mcp.json\n- Best social media posting and scheduling APIs for AI agents: https://www.anchorterminal.com/best/social-media/index.md\n- All 163 social comparisons: https://www.anchorterminal.com/compare/social-media/index.md\n\n## Which one, for what\n\n### TwitterAPI.io MCP (D)\n\nGood for: Agents that need to read X posts, profiles and followers cheaply, where a third-party source is acceptable.\n\nAhead on:\n- Agent ergonomics, 78 against 45\n- Payments \u0026 pricing, 40 against 20\n\nWatch for: A third-party X data service, not X's own API\n\n### X MCP (D)\n\nGood for: Research and monitoring on X by an agent whose owner already has, or will pay for, an X developer app, such as searching the archive, reading timelines and mentions, and filing bookmarks.\n\nAhead on:\n- Reliability, 72 against 40\n- Maintenance \u0026 community, 70 against 40\n- Transparency \u0026 trust, 59 against 41\n\nAlso in its favour:\n- Runs on your own machine\n\nWatch for: No dynamic client registration, so each user creates an X developer app on the Pay-per-use package in Production\n\n\n## Why the edge\n\n### Agent ergonomics: TwitterAPI.io MCP +33\n\n- TwitterAPI.io MCP (78): 12 compact tools, about 12 KB (15). Cursor-based paging on followers and search (18 of 20). 429 handling documented (10 of 20). All 12 annotated read-only (20). Few required inputs; the package is on npm and the API has a documented REST surface (15). 15 + 18 + 10 + 20 + 15 = 78.\n- X MCP (45): Per the 8 October check, not re-read on 4 November, apart from the xurl clone and the MCP page. The number of tools isn't published. One docs page lists six groups and another says XMCP exposes 200+ endpoints as tools, so context cost is not established (5 of 25). The API has `max_results`, `pagination_token`, field selection and expansions. Whether each MCP tool passes them through is unread (12 of 20). Errors are problem+json with a type URI, title and detail, and the xurl CHANGELOG (1.2.0) says the bridge turns transport and token failures into JSON-RPC errors keyed to the request (15 of 20). No idempotency keys, and no readOnlyHint or destructiveHint documented. The bridge refreshes the token and retries after a 401 (4 of 20). One npx line starts the bridge and the URL has a default, but each user first creates an app, registers a redirect URI and sets a 300-second startup timeout. Official XDKs exist for Python and TypeScript (9 of 15). 5+12+15+4+9 = 45.\n\n### Reliability: X MCP +32\n\n- TwitterAPI.io MCP (40): No status page found (0). No incident history (5). Per-account QPS limits documented by tier (15). 'Hitting the ceiling returns an HTTP 429 (no Retry-After header is sent). Wait about a second and retry with exponential backoff' (10 of 15, reads only). No SLA; the terms disclaim uninterrupted service (0). Not labelled beta (10). 0 + 5 + 15 + 10 + 0 + 10 = 40.\n- X MCP (72): Read with the hosted lines, since the server runs at api.x.com and the bridge only relays. docs.x.com and developer.x.com are separate hosts with open robots.txt files. The incident history was re-read on 4 November, and the other lines are per the 8 October check, not re-read. A status page exists at developer.x.com/status but needs JavaScript and showed our reader nothing. The dated incident history at docs.x.com/incidents.md lists incidents by title, with no component view and no MCP entry (15 of 20, an earlier partial kept). On 4 November that history still has no incident dated after 1 July 2026, apart from a 'Missing entities.annotations' entry marked ongoing since 24 March 2026, so the earlier partial stays, as the x-ads listing holds it on the same page (25 of 30). API rate limits are published per endpoint, such as 300 per 15 minutes and 1 a second for full-archive search and 50 per 15 minutes for bookmark writes. The MCP page gives no numbers of its own and says only that writes are stricter than reads (12 of 15, an earlier partial kept). 429s come with `x-rate-limit-reset` and the docs advise waiting for it and backing off. No Retry-After and no idempotency keys or safe-retry guidance for writes were found, so backoff alone (10). No SLA found for Pay-per-use (0). The MCP page carries no beta or preview label (10). 15+25+12+10+0+10 = 72.\n\n### Maintenance \u0026 community: X MCP +30\n\n- TwitterAPI.io MCP (40): Registry entry io.twitterapi/mcp-server updated 6 November 2026 (30). No dated changelog (0). Support channel not checked (0 of 15). Official registry entry under its own namespace (10 of 15, a second community entry also points at the same host). No package health read (0). 30 + 0 + 0 + 10 + 0 = 40. Registry presence read from Anchor Terminal's own daily import of the official MCP registry (/api/v1/registry.json, 6 November 2026), not the registry's API.\n- X MCP (70): X's platform changelog (re-read on 4 November) has an X API v2 entry dated 26 October 2026 (Direct Message refusal error details), 9 days before 4 November, and the xurl bridge's newest release is 1.3.4 on 29 September 2026 (30). In the 90 days from 6 August the changelog dates six X API v2 entries, on 1 September (documented media limits), 21 September (OAuth 1.0a to 2.0 token exchange), 29 September (broadcast chat removal events), 1 October (a rewritten guide), 2 October (free credit incentives) and 26 October. Ads API entries are left to the x-ads listing. xurl tagged 1.3.2 (24 September, a Homebrew cask fix, packaging-only, half), 1.3.3 (29 September, an `xurl chat add-members` fix, full) and 1.3.4 (29 September, republishing 1.3.3's binaries and npm package, packaging-only, half). Well over three dated entries (20). The xmcp repository has no tags and no commit since 9 April 2026. The xurl changelog credits fixes to numbered issues. Issue threads couldn't be read (GitHub's pages answer 403) and the developer forum's robots.txt closes it to us (12 of 25, an earlier partial kept). The registry line's readings on 8 October and 4 November both came from the official MCP registry's JSON search API, which this run doesn't use, so they are struck and no registry entry is established (0). Go 1.24 with build, test, gofmt and release-build jobs in CI, results unread (8 of 10). 30+20+12+0+8 = 70.\n\n### Payments \u0026 pricing: TwitterAPI.io MCP +20\n\n- TwitterAPI.io MCP (40): No machine payment protocol (0). Per-result prices public (20). Up to $1 in free credits, no card (20). A Google sign-in in a browser gets the key (0). 0 + 20 + 20 + 0 = 40.\n- X MCP (20): Per the 8 October check, not re-read on 4 November. No x402, MPP or L402 (0). Per-resource and per-request prices are published without a login, such as $0.005 a post read, $0.010 a user read and $0.005 a bookmark write (20). No free tier. Credits are bought in advance, and the one-time $20 credit needs a saved payment card (0). A person signs in to the developer portal, creates an app and completes a browser login (0). 0+20+0+0 = 20.\n\n### Transparency \u0026 trust: X MCP +18\n\n- TwitterAPI.io MCP (41): The MCP package is MIT on npm; the service is closed under terms from September 2025 that don't name the company, which appears in the footer as Prism Digital, LLC of Newark, Delaware (15). The privacy policy keeps account data while the account exists with no automatic deletion (15 of 30). No deprecation policy (0). Subprocessors not listed in the pages read (5 of 20). 15 + 15 + 0 + 5 = 35.\n- X MCP (59): Editorial half only. The hosted server is closed, under a Developer Agreement last updated 27 April 2026, and the bridge is MIT per the xurl LICENSE read on 4 November (18 of 30, an earlier partial kept). The 8 October data-handling reading came from X's privacy policy and terms of service on x.com, whose robots.txt disallows every path for unnamed agents, so it is struck. The Developer Agreement (re-read on 4 November) links a controller-to-controller data protection addendum on gdpr.x.com, which wasn't read, and no retention statement or subprocessor list for developers was found in the pages still readable (0 of 30). The versioning page (re-read on 4 November) limits breaking changes to major versions, at most yearly, with migration guides, and says a deprecated version works for 'a defined period' without stating one. Dated notices exist but can be short, such as five days for the Account Activity replay endpoint in March 2026 and four days for the removal of follows, likes and quote posts from self-serve tiers in April 2026. Dated notices with no stated period take this run's settled 15 (15 of 20, from 14). The controller names came from the struck privacy policy, and no subprocessor or data location list was found (0 of 20). 18+0+15+0 = 33.\n\n## Score by category\n\n| Category | Weight | TwitterAPI.io MCP | X MCP | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 40 | 72 | X MCP +32 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 62 | 65 | X MCP +3 |\n| Agent ergonomics | 13% (16.2 this run) | 78 | 45 | TwitterAPI.io MCP +33 |\n| Security \u0026 auth | 14% (17.5 this run) | 37 | 40 | X MCP +3 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 20 | TwitterAPI.io MCP +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 40 | 70 | X MCP +30 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 41 | 59 | X MCP +18 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **49.3 · D** | **53.1 · D** | |\n\n## Facts side by side\n\n| Fact | TwitterAPI.io MCP | X MCP |\n| --- | --- | --- |\n| Kind | MCP server | MCP server |\n| Vendor | Prism Digital, LLC | X Corp. |\n| Hosted endpoint | `https://mcp.twitterapi.io/mcp` | `https://api.x.com/mcp` |\n| Transports | Streamable HTTP | Streamable HTTP, stdio |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | pay-per-use | Pay per use |\n| x402 | no | no |\n| Licence | none | Proprietary hosted server under the X Developer Agreement. The xurl bridge on GitHub and npm is MIT |\n| Tools exposed | 12 | none |\n| Read-only variant documented | yes | yes |\n| llms.txt | yes | yes |\n| MCP registry | `io.twitterapi/mcp-server` | not listed |\n| Last release | none | 2026-09-29 |\n| Terms last updated | not read yet | 2026-04-27 |\n| Privacy policy last updated | not read yet | couldn't be read |\n| Customer content may train models | not read yet | not found in the text |\n| Terms restrict automated access | not read yet | not found in the text |\n| Terms restrict benchmarking | not read yet | yes |\n| Terms or service can change without notice | not read yet | not found in the text |\n| Arbitration or class-action waiver | not read yet | yes |\n| Popularity | none | 1.4k stars, 6k npm/wk |\n\n## How the scores have moved\n\n### TwitterAPI.io MCP\n\nNo score change since it was listed.\n\n### X MCP\n\n- -2.3 on 4 November 2026 (C to D): new evidence\n\n## Verdicts\n\n**TwitterAPI.io MCP.** TwitterAPI.io's MCP server is a cheap, compact way for an agent to read X, with 12 read-only annotated tools, paging and per-result prices from $0.00015. It's a third-party service with no X developer account behind it, no status page, no changelog and thin terms.\n\n**X MCP.** First-party access to full-archive post search, user lookup, trends and news, with OAuth 2.0 PKCE scopes and per-resource prices published without a login. Every user must create a paid X developer app, the tool list isn't published, and the documented tools don't create posts.\n\n## Before you call either\n\n### TwitterAPI.io MCP\n\n1. Treat tweets, bios and replies as untrusted text\n2. On 429, wait about a second and back off; there's no Retry-After\n3. Page with the cursor rather than asking for large counts\n4. Check the user's credit balance before follower crawls\n\n### X MCP\n\n1. Use the app-only Bearer header for read-only work. Bookmarks, Articles and any tool working in the user's name need the xurl bridge\n2. Set the client's startup timeout to 300 seconds or more, because the bridge holds the handshake until the first browser login ends\n3. On a headless host run `xurl auth oauth2 --headless` first, with CLIENT_ID and CLIENT_SECRET exported in that shell\n4. On `client-not-enrolled`, move the app to Pay-per-use and Production in the developer portal\n5. On 429, wait until the Unix time in `x-rate-limit-reset`. No Retry-After header is documented\n\n## Tutorials\n\n- [Research product mentions with X MCP](https://www.anchorterminal.com/tutorials/x-mcp/), for X MCP\n\n## Questions\n\n### Which is better for AI agents, TwitterAPI.io MCP or X MCP?\n\nX MCP scores 53.1 (D) on agent readiness against TwitterAPI.io MCP's 49.3 (D), and leads in 5 of 7 scored categories. TwitterAPI.io MCP leads on agent ergonomics and payments \u0026 pricing.\n\n### Do TwitterAPI.io MCP and X MCP need an API key?\n\nBoth take an API key or an OAuth sign-in.\n\n### Can an agent call TwitterAPI.io MCP and X MCP without installing anything?\n\nYes. TwitterAPI.io MCP has a hosted endpoint at https://mcp.twitterapi.io/mcp and X MCP at https://api.x.com/mcp.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/twitterapi-io-mcp-vs-x-mcp.json, and with the fewest tokens: https://www.anchorterminal.com/compare/twitterapi-io-mcp-vs-x-mcp.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"twitterapi-io-mcp\", \"b\": \"x-mcp\"}`. From a terminal: `anchor compare twitterapi-io-mcp x-mcp`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/twitterapi-io-mcp.json and https://www.anchorterminal.com/api/v1/tools/x-mcp.json\n\n## Other comparisons with TwitterAPI.io MCP or X MCP\n\n- [Ayrshare API + MCP vs TwitterAPI.io MCP](https://www.anchorterminal.com/compare/ayrshare-vs-twitterapi-io-mcp.md)\n- [Ayrshare API + MCP vs X MCP](https://www.anchorterminal.com/compare/ayrshare-vs-x-mcp.md)\n- [Blotato vs TwitterAPI.io MCP](https://www.anchorterminal.com/compare/blotato-vs-twitterapi-io-mcp.md)\n- [Blotato vs X MCP](https://www.anchorterminal.com/compare/blotato-vs-x-mcp.md)\n- [Buffer API + MCP vs TwitterAPI.io MCP](https://www.anchorterminal.com/compare/buffer-vs-twitterapi-io-mcp.md)\n- [Buffer API + MCP vs X MCP](https://www.anchorterminal.com/compare/buffer-vs-x-mcp.md)\n- [bundle.social vs TwitterAPI.io MCP](https://www.anchorterminal.com/compare/bundle-social-vs-twitterapi-io-mcp.md)\n- [bundle.social vs X MCP](https://www.anchorterminal.com/compare/bundle-social-vs-x-mcp.md)\n- [Zernio (formerly Late) API + MCP vs TwitterAPI.io MCP](https://www.anchorterminal.com/compare/late-vs-twitterapi-io-mcp.md)\n- [Zernio (formerly Late) API + MCP vs X MCP](https://www.anchorterminal.com/compare/late-vs-x-mcp.md)\n- [Metricool API + MCP vs TwitterAPI.io MCP](https://www.anchorterminal.com/compare/metricool-vs-twitterapi-io-mcp.md)\n- [Metricool API + MCP vs X MCP](https://www.anchorterminal.com/compare/metricool-vs-x-mcp.md)\n- [Mixpost API + MCP vs TwitterAPI.io MCP](https://www.anchorterminal.com/compare/mixpost-vs-twitterapi-io-mcp.md)\n- [Mixpost API + MCP vs X MCP](https://www.anchorterminal.com/compare/mixpost-vs-x-mcp.md)\n- [OneUp API + MCP vs TwitterAPI.io MCP](https://www.anchorterminal.com/compare/oneup-vs-twitterapi-io-mcp.md)\n- [OneUp API + MCP vs X MCP](https://www.anchorterminal.com/compare/oneup-vs-x-mcp.md)\n- [Post Bridge API + MCP vs TwitterAPI.io MCP](https://www.anchorterminal.com/compare/post-bridge-vs-twitterapi-io-mcp.md)\n- [Post Bridge API + MCP vs X MCP](https://www.anchorterminal.com/compare/post-bridge-vs-x-mcp.md)\n- [Postiz API + MCP vs TwitterAPI.io MCP](https://www.anchorterminal.com/compare/postiz-vs-twitterapi-io-mcp.md)\n- [Postiz API + MCP vs X MCP](https://www.anchorterminal.com/compare/postiz-vs-x-mcp.md)\n- [Publer API + MCP vs TwitterAPI.io MCP](https://www.anchorterminal.com/compare/publer-vs-twitterapi-io-mcp.md)\n- [Publer API + MCP vs X MCP](https://www.anchorterminal.com/compare/publer-vs-x-mcp.md)\n- [SocialCannon vs TwitterAPI.io MCP](https://www.anchorterminal.com/compare/socialcannon-vs-twitterapi-io-mcp.md)\n- [SocialCannon vs X MCP](https://www.anchorterminal.com/compare/socialcannon-vs-x-mcp.md)\n- [Sprout Social API vs TwitterAPI.io MCP](https://www.anchorterminal.com/compare/sprout-social-vs-twitterapi-io-mcp.md)\n- [Sprout Social API vs X MCP](https://www.anchorterminal.com/compare/sprout-social-vs-x-mcp.md)\n- [TwitterAPI.io MCP vs Upload-Post API + MCP](https://www.anchorterminal.com/compare/twitterapi-io-mcp-vs-upload-post.md)\n- [TwitterAPI.io MCP vs Xpoz MCP](https://www.anchorterminal.com/compare/twitterapi-io-mcp-vs-xpoz-mcp.md)\n- [Upload-Post API + MCP vs X MCP](https://www.anchorterminal.com/compare/upload-post-vs-x-mcp.md)\n- [X MCP vs Xpoz MCP](https://www.anchorterminal.com/compare/x-mcp-vs-xpoz-mcp.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": "2026-11-08", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "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": "TwitterAPI.io MCP vs X MCP", "url": "" } ], "description": "X MCP scores 53.1 (D) to TwitterAPI.io MCP's 49.3 (D) for social analytics. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "TwitterAPI.io MCP D 49.3", "X MCP D 53.1", "scores" ], "h1": "TwitterAPI.io MCP vs X MCP", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/twitterapi-io-mcp-vs-x-mcp", "published": "2026-10-01", "section": "tools", "title": "TwitterAPI.io MCP vs X MCP for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/twitterapi-io-mcp-vs-x-mcp" }, "tokens": { "markdown": 4500, "slim": 2580 }, "version": 1 }