{ "data": { "a": { "slug": "databar", "name": "Databar", "vendor": "Databar, Inc.", "vendorUrl": "https://databar.ai", "kind": "http-api", "category": "lead-data", "summary": "Databar is a data enrichment platform from Databar, Inc. that reaches 100+ providers for company, person, email and phone data through tables, waterfalls and flows, with a REST API, Python SDK, CLI and a hosted MCP server.", "url": "https://www.anchorterminal.com/tools/databar", "markdownUrl": "https://www.anchorterminal.com/tools/databar.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/databar.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/databar.json", "dns": "databar.grade.anchorterminal.com", "license": "Proprietary, under Databar, Inc.'s terms of service", "transports": [ "http", "streamable-http", "sse" ], "remoteUrl": "https://mcp.databar.ai/mcp", "packages": [ { "registry": "pypi", "name": "databar" } ], "auth": "mixed", "authNotes": "REST: workspace API key in the `x-apikey` header, from Integrations in the workspace. MCP: OAuth through Databar's own consent screen, with a Connected apps page to revoke access, or the API key as a Bearer token. No scopes found; the terms let Databar revoke or rotate keys.", "pricing": "paid", "pricingNotes": "Build $99 a month for 5,000 credits, Scale $495 for 50,000, Enterprise custom; annual saves 12% with the year's credits up front. Free plan with 150 credits and no API access. 14-day premium trial with no card. Credits per connector vary (for example 0.15 credits per Google Maps location) and are only spent on Databar's provider keys; your own keys use actions (https://databar.ai/pricing, https://docs.databar.ai/product-guide/credits-and-billing, checked 2026-11-06).", "priceSummary": "$0.0198 / credit", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in llms.txt, the API reference, MCP docs or pricing (checked 2026-11-06). An empty balance answers 406.", "endpoints": [] }, "toolCount": 69, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://docs.databar.ai", "llmsTxt": "https://docs.databar.ai/llms.txt", "capabilities": [ "lead.enrichment", "email.finder", "email.verification", "lead.search", "data.company" ], "tags": [ "hosted", "mcp", "remote-mcp", "oauth", "llms-txt", "python", "cli", "async-jobs", "enrichment", "free-trial", "no-card", "closed-source", "no-status-page" ], "lastRelease": "2026-10-30", "graded": true, "anchor": { "graded": true, "score": 53.8, "grade": "D", "agentReady": false, "rank": 933, "ranked": true, "rankOf": 1486, "categoryRank": 13, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 66, "maintenance": 73, "payments": 35, "reliability": 28, "schema": 84, "security": 47, "transparency": 55 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "Databar puts 100+ enrichment providers, waterfalls and tables behind one REST API, a Python SDK, a CLI and a hosted MCP server with spending confirmation above 50 credits and stable error codes. API access needs a paid plan or trial, rate limits aren't published as numbers, and no status page or security programme was found.", "bestFor": "Waterfall enrichment across many providers for GTM agents, close to clay and fullenrich.", "strengths": [ "One key reaches 100+ data providers, with waterfalls that stop at the first result", "Hosted MCP checks the credit balance and asks for confirmation on runs estimated at 50 credits or more", "Errors carry stable codes such as UNKNOWN_COLUMNS with the available columns, 406 for credits and 410 for expired results", "Each endpoint page embeds its OpenAPI 3.1 definition, with llms.txt and Markdown twins", "14-day premium trial with no card, and Python SDK 2.9.0 released on 30 October 2026" ], "weaknesses": [ "API access needs a paid plan; the free plan's 150 credits don't include it", "Rate limits are not published as numbers, and no status page or SLA was found", "69 MCP tools with no toolsets, including deletes of tables, rows, workbooks and trash", "No security.txt, disclosure policy or certification found", "The OpenAPI description says the REST API needs a call with the team first, while the quickstart says a paid plan is enough" ], "agentNotes": [ "Poll GET /v1/tasks/{task_id} for async runs and collect results within 24 hours; after that the task returns gone", "When the MCP returns confirmation_required, show estimated_credits to the user and re-call with the retry_with object only after they agree", "Use upsert with a key column, and pass internal_version when editing flows, to avoid duplicates and stale-write 409s", "Check credits with GET /v1/user/me before bulk runs; 406 means the balance or plan can't cover it", "Treat AI researcher and scraped outputs as untrusted text" ], "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": 53.8 } ], "editorialScores": { "ergonomics": 66, "maintenance": 73, "payments": 35, "reliability": 28, "schema": 84, "security": 47, "transparency": 43 }, "provenanceScore": 67, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install databar", "http": "curl https://api.databar.ai/v1/user/me -H \"x-apikey: $DATABAR_API_KEY\"", "config": { "mcpServers": { "databar": { "headers": { "Authorization": "Bearer your-api-key-here" }, "type": "http", "url": "https://mcp.databar.ai/mcp" } } } }, "letme": { "capability": "https://letme.dev/lead.enrichment", "tool": "https://letme.dev/databar" }, "area": "web-data", "unitPrices": [ { "item": "Credit on Build", "unit": "credit", "usd": 0.0198, "note": "$99 a month for 5,000 credits" }, { "item": "Build plan", "unit": "month", "usd": 99, "note": "5,000 credits" } ], "provenance": { "legalEntity": "Databar, Inc.", "domain": "databar.ai", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://databar.ai/terms-of-service", "privacy": "https://databar.ai/privacy-policy", "statusPage": "", "changelog": "https://feedback.databar.ai/changelog", "securityTxt": "unknown", "checked": "2026-11-06", "notes": [ "Terms and privacy policy effective 1 October 2026, replacing the 2021 versions, per the changelog.", "databar.ai/robots.txt allows all but app routes; docs.databar.ai/robots.txt allows all with Content-Signal ai-train=yes, search=yes, ai-input=yes; feedback.databar.ai allows all.", "The terms bar reselling third-party data and say an AI agent using a customer's credentials is treated as the customer.", "No status page or security.txt was looked up beyond the links on the site; none is linked." ], "score": 67 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/databar.json", "live": { "slug": "databar", "probe": { "target": "https://mcp.databar.ai/mcp", "method": "get", "lastAt": "2026-11-07T18:20:19.847046439Z", "lastOk": true, "lastStatus": 401, "lastMs": 312, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 266, "p95ms24h": 345, "samples24h": 200, "samples30d": 200, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 187, "ok": 187 } ] }, "versions": [ { "registry": "pypi", "name": "databar", "version": "2.9.0", "released": "2026-10-30", "seenAt": "2026-11-06T23:19:17.79768289Z" } ], "pypiWeekly": 140, "securityTxt": { "url": "https://databar.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:19.585020171Z" }, "llmsTxt": { "url": "https://docs.databar.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:14.255704247Z" }, "pages": [ { "url": "https://feedback.databar.ai/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:09:44.198444657Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "74531355b07b" }, { "url": "https://databar.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:02:24.391544522Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "531d3fecc8b0" }, { "url": "https://databar.ai/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:02:27.152620002Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "675056868ed7" }, { "url": "https://databar.ai/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:02:28.980639136Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e6dbfaf05e9f" } ], "mcpTools": { "url": "https://mcp.databar.ai/mcp", "checkedAt": "2026-11-07T01:43:41.829002126Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-11-07T01:43:41.829002126Z" }, "updatedAt": "2026-11-07T18:20:19.847046439Z" } }, "answer": "Databar scores 53.8 (D) on agent readiness against Fuse MCP's 44.3 (E), and leads in 6 of 7 scored categories. Fuse MCP leads on reliability.", "b": { "slug": "fuse-mcp", "name": "Fuse MCP", "vendor": "FuseAI, LLC", "vendorUrl": "https://fuseai.com", "kind": "mcp", "category": "lead-data", "summary": "Fuse MCP is the hosted MCP server for Fuse AI's sales platform. It lets an assistant search people and companies, enrich contacts, manage lists and campaigns, and send email and LinkedIn messages from a signed-in Fuse account.", "url": "https://www.anchorterminal.com/tools/fuse-mcp", "markdownUrl": "https://www.anchorterminal.com/tools/fuse-mcp.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/fuse-mcp.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/fuse-mcp.json", "dns": "fuse-mcp.grade.anchorterminal.com", "license": "Proprietary hosted service under FuseAI's terms of service. No public source repository found", "transports": [ "streamable-http" ], "remoteUrl": "https://mcp.fuseai.com", "packages": [], "auth": "oauth", "authNotes": "Access is self-serve. The client registers itself by dynamic client registration, then a person signs in to their Fuse account in a browser (email and password, Google or Microsoft, with a verified email address) and approves the connection. The flow is authorisation code with PKCE (S256) and the single scope `mcp:tools`. The connection runs as that user with all of their permissions. Access tokens last one hour, refresh tokens rotate on each use and last 30 days from last use. There is no API-key route into the MCP server. The separate REST API takes `af_` keys over HTTP Basic, limited to any of nine scopes.", "pricing": "freemium", "pricingNotes": "Free plan at $0, then Solo $60 a month with 480,000 credits a year and Team $200 a month with 1,200,000, with 20 per cent off for annual billing. Enterprise is by quote. The pricing page gives the Free allowance as 24,000 credits a year on the plan card and 2,000 in the usage table. MCP calls spend the same credits as the app, and every call needs a balance of at least 100. The Solo card lists MCP among its integrations, and we could not confirm from the page that the Free plan includes it. Top-up prices are shown only in the app. We did not attempt signup, so whether a card is asked for is unchecked (https://fuseai.com/pricing, checked 2026-10-08).", "priceSummary": "$60 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the MCP docs, the REST docs, the OpenAPI spec or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": 290, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://docs.fuseai.com/mcp/connect", "llmsTxt": "https://docs.fuseai.com/llms.txt", "openapi": "https://docs.fuseai.com/openapi.json", "capabilities": [ "lead.search", "lead.enrichment", "email.finder", "email.verification", "data.company", "email.send", "search.research" ], "tags": [ "hosted", "mcp", "oauth", "freemium", "sales", "outreach", "enrichment", "lead-search", "llms-txt", "openapi", "closed-source", "new" ], "lastRelease": "2026-10-07", "graded": true, "anchor": { "graded": true, "score": 44.3, "grade": "E", "agentReady": false, "rank": 1212, "ranked": true, "rankOf": 1486, "categoryRank": 19, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 57, "maintenance": 35, "payments": 30, "reliability": 40, "schema": 50, "security": 43, "transparency": 52 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": 0, "verdict": "The server documents 290 tools with read-only and destructive annotations, OAuth with PKCE and dynamic client registration, and published limits of 60 requests a minute. The single `mcp:tools` scope grants everything the user can do, sends happen at once with no undo, and no status page, changelog or security contact was found.", "bestFor": "Suited to a salesperson or founder who wants an assistant to build prospect lists, enrich them and run email and LinkedIn outreach inside one Fuse account.", "strengths": [ "Every tool carries `readOnlyHint` or `destructiveHint` per the docs, and the tool reference marks 113 read-only, 144 writing and 33 destructive", "OAuth authorisation code with PKCE and dynamic client registration, one-hour access tokens and rotating refresh tokens", "MCP limits are published at 60 requests a minute and 5,000 a day per user, with `RATE_LIMIT_EXCEEDED` on 429", "Credit costs per action are public, reads are free, and `get_credit_prices` returns current prices before a call", "llms.txt, Markdown twins of every docs page and a skill file, per the 8 October check" ], "weaknesses": [ "The only OAuth scope is `mcp:tools`, so a connection can do everything its user can, including sending email and LinkedIn messages", "The 290 tools come to about half a megabyte of descriptions and schemas, with no toolsets or read-only subset", "The October 2026 rebuild removed the earlier tools such as `prospect_search`, and the docs say the server does not announce tool list changes", "No status page, changelog, SLA, security.txt or disclosure contact was found on the site or in the docs", "Vendor pages disagree on the Free allowance (24,000 credits a year or 2,000) and on the provider count (40+, 39 or 20+)" ], "agentNotes": [ "Keep the client's approval prompt on for every tool that is not read-only. Sends, CRM pushes and Slack posts run at once with no undo", "Launch a campaign only on an explicit request. Creating one makes a draft, and `update_campaign_status_tool` starts real outreach", "Call `get_credits_balance` and `get_credit_prices` first. Every call needs at least 100 credits, and searches cost 2 credits a result", "Resolve filter values with `lookup_filter_values` or `get_company_search_enums` before `search_people` or `search_companies`", "Start long work with `deep_research_start`, then poll `deep_research_status`. A tool call has 60 seconds, and runs take 5 to 20 minutes" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "E", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 44.3 } ], "editorialScores": { "ergonomics": 57, "maintenance": 35, "payments": 30, "reliability": 40, "schema": 50, "security": 43, "transparency": 36 }, "provenanceScore": 67, "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": { "claudeCode": "claude mcp add --transport http fuse https://mcp.fuseai.com", "config": { "mcpServers": { "fuse": { "url": "https://mcp.fuseai.com" } } } }, "letme": { "capability": "https://letme.dev/lead.search", "tool": "https://letme.dev/fuse-mcp" }, "area": "web-data", "unitPrices": [ { "item": "Free plan", "unit": "month", "usd": 0, "note": "1 seat. The pricing page shows 24,000 credits a year on the plan card and 2,000 in the usage table" }, { "item": "Solo plan", "unit": "month", "usd": 60, "note": "1 seat, 480,000 credits a year" }, { "item": "Team plan", "unit": "month", "usd": 200, "note": "5 seats, 1,200,000 credits a year" } ], "provenance": { "legalEntity": "FuseAI, LLC", "domain": "fuseai.com", "domainRegistered": "2017-03-11", "endpointOnVendorDomain": true, "terms": "https://fuseai.com/legal/terms-of-service", "privacy": "https://fuseai.com/legal/privacy-policy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The terms of service (last updated 1 July 2026) give the contracting party as FuseAI, LLC with the contact hello@tryfuse.ai and no postal address. The company page says the team is in San Francisco.", "The MCP server answers at mcp.fuseai.com and its authorisation server at core.backend.fuseai.com. The REST API is on api.tryfuse.ai, the vendor's earlier domain, and tryfuse.ai redirects to fuseai.com.", "fuseai.com/.well-known/security.txt and docs.fuseai.com/.well-known/security.txt return 404.", "No status page or changelog is linked from the site, the docs index or the sitemap. status.fuseai.com, status.tryfuse.ai and trust.fuseai.com did not connect from our network.", "RDAP for fuseai.com gives a registration date of 2017-03-11, so the domain predates the company's use of it. The domain's history before Fuse was not checked." ], "score": 67 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/fuse-mcp.json", "live": { "slug": "fuse-mcp", "probe": { "target": "https://mcp.fuseai.com", "method": "mcp-initialize", "lastAt": "2026-11-07T18:20:26.372611401Z", "lastOk": true, "lastStatus": 401, "lastMs": 475, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 357, "p95ms24h": 476, "samples24h": 239, "samples30d": 7463, "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": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 248, "ok": 248 }, { "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": 187, "ok": 187 } ] }, "securityTxt": { "url": "https://fuseai.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:00:47.530262988Z" }, "llmsTxt": { "url": "https://docs.fuseai.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:33.231030808Z" }, "domain": { "domain": "fuseai.com", "registered": "2017-03-11", "source": "https://rdap.verisign.com/com/v1/domain/fuseai.com", "checkedAt": "2026-11-01T14:19:53.148141083Z" }, "pages": [ { "url": "https://fuseai.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:10:19.515202283Z", "changedAt": "2026-11-07T14:10:19.515202283Z", "fingerprint": "6b03613a4663" }, { "url": "https://fuseai.com/legal/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:10:15.123163925Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "d35ecd9cf6d0" }, { "url": "https://fuseai.com/legal/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:10:17.617324592Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "911a898c524d" } ], "mcpTools": { "url": "https://mcp.fuseai.com", "checkedAt": "2026-11-07T01:44:40.572315514Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-10-08T21:33:51.293613327Z" }, "updatedAt": "2026-11-07T18:20:26.372611401Z" } }, "edges": [ { "by": 38, "category": "maintenance", "leads": "databar", "name": "Maintenance \u0026 community", "reasons": { "a": "Closed service. Python SDK 2.9.0 on 30 October 2026, 7 days before this check (30). SDK 2.7.0 and 2.8.0 on 6 October and changelog entries on 23, 24, 27, 28, 29 and 30 September and 1 October (20). A public changelog, roadmap and feedback portal, an email address, and a Slack channel on Scale (10 of 15). An official Python SDK and CLI, no other languages (10 of 15). Package health not checked (3 of 10). 30+20+10+10+3 = 73.", "b": "Readings are per the 8 October check, not re-read on 4 November 2026. The tool reference is dated 7 October 2026 and records the October 2026 rebuild of the tool list, within 30 days today (30); it drops to 20 after 6 November unless a newer dated change appears. No changelog or release notes found, so three dated entries in 90 days could not be shown (0). No public changelog or issue tracker. Support is by email at support@fuseai.com, not tested (5 of 15). No readable registry page names the server and no official SDK was found (0). No package to assess (0 of 10). 30 + 0 + 5 + 0 + 0 = 35." }, "scores": { "a": 73, "b": 35 } }, { "by": 34, "category": "schema", "leads": "databar", "name": "Schema \u0026 documentation", "reasons": { "a": "Each API reference page embeds its OpenAPI 3.1 operation (spec version 0.1.2), with no downloadable file found (20 of 25). llms.txt with 79 API entries and Markdown twins (10). Descriptions say when to use each endpoint, such as headless runs against table runs, and what a delete leaves behind (16 of 20). Typed request bodies with required fields (12 of 15). An error envelope with stable codes and examples for 400, 406 and 422 (14 of 15). v1 paths and a dated changelog, though the API's own versioning isn't described (12 of 15). 20+10+16+12+14+12 = 84.", "b": "Readings are per the 8 October check, not re-read on 4 November 2026, since FuseAI's terms bar automated extraction from its website and docs. Contract line 0 (was 22 of 25). The MCP tool schemas were never read, because tools/list needs a signed-in account, and the docs only say every tool ships one. The 8 October reading leaned on the REST API's OpenAPI file, a separate surface, and no reading records a docs page that shows or links it, so it is struck for this line, as jambonz's and stable-audio's were. llms.txt, Markdown twins of every page and a skill file (10). The tool reference shows descriptions that state purpose, the preferred tool for a job and when a destructive tool may be called (16 of 20). Enum lookup tools such as `get_company_search_enums` exist, but input constraints were not read first-hand (9 of 15). Error results are documented with codes and two JSON examples, plus four plain-text failures, and the docs say the codes do not always match the REST catalogue (12 of 15). No changelog was found and the docs say the server does not announce changes to the tool list. The tool reference is dated 7 October 2026 (3 of 15). 0 + 10 + 16 + 9 + 12 + 3 = 50." }, "scores": { "a": 84, "b": 50 } }, { "by": 12, "category": "reliability", "leads": "fuse-mcp", "name": "Reliability", "reasons": { "a": "Hosted lines. No status page linked from the site or docs (0). No incident history to read (5). The 20 August changelog says rate limits return 429, but no numbers were found in the docs read (5 of 15). The SDK backs off on 429 per the 28 September entry, tasks can be cancelled with a refund, and no Retry-After or idempotency key is documented (8 of 15). No SLA found (0). The MCP server left beta on 15 July 2026 and the API is generally available (10). 0+5+5+8+0+10 = 28.", "b": "Graded as a hosted service. FuseAI's terms bar automated systems or scripts from extracting content from the Services, which they define to include the website, so every fuseai.com page keeps its 8 October reading, not re-read on 4 November 2026. No status page is linked from the site, the docs or the sitemap (0). No readable incident history (5). MCP limits are published at 60 requests a minute and 5,000 a day per user (15). The server answers 429 with `RATE_LIMIT_EXCEEDED` and the docs say to back off and retry. No `Retry-After` is documented for the MCP server and there are no idempotency keys, so backoff guidance alone (10). No SLA found (0). The server carries no beta or preview label (10). 0 + 5 + 15 + 10 + 0 + 10 = 40." }, "scores": { "a": 28, "b": 40 } }, { "by": 9, "category": "ergonomics", "leads": "databar", "name": "Agent ergonomics", "reasons": { "a": "69 MCP tools with no toolsets found (5), and REST row reads sized by `per_page` with `has_next_page` (10 of 25 for the two together). Pagination, row filters and a search parameter on enrichments (16 of 20). Errors name the fix, such as unknown columns with the available ones, 406 for credits, 409 for a stale `internal_version` and 410 for expired results (18 of 20). Upserts by key, version tokens on flow edits, cancel with refund, and MCP confirmation above 50 credits; MCP tool annotations not confirmed (13 of 20). Python SDK and a CLI, one language (9 of 15). 10+16+18+13+9 = 66.", "b": "Readings are per the 8 October check, not re-read on 4 November 2026. 290 tools and about half a megabyte of definitions, with no toolsets, dynamic loading or read-only subset. The docs warn that some clients pass only the first 40 tools (5 of 25). List reads return a `data` array with `pagination`, searches return a scroll token or cursor, and tools take limits and filters (18 of 20). Rejected calls set `isError` and return codes such as `TOOL_ARGUMENT_VALIDATION_FAILED` with the missing field named. Other failures are short plain text (15 of 20). The docs say every tool carries `readOnlyHint` or `destructiveHint`, which we could not read from the server. No idempotency keys, and sends are not marked destructive (14 of 20). No official SDK found, and most changes need an id looked up first (5 of 15). 5 + 18 + 15 + 14 + 5 = 57." }, "scores": { "a": 66, "b": 57 } }, { "by": 5, "category": "payments", "leads": "databar", "name": "Payments \u0026 pricing", "reasons": { "a": "No x402, MPP or L402 (0). Plan prices and credits are public, and each connector's credit cost is shown before a run and in the enrichment's pricing field; credits aren't sold per call outside a plan (15 of 20). A 14-day premium trial with no card, per the pricing FAQ (20). A person signs up in a browser, and API access needs a paid plan (0). 0+15+20+0 = 35.", "b": "Readings are per the 8 October check, not re-read on 4 November 2026. No x402, MPP or L402 (0). Plan prices and the credit cost of each action are public, and `get_credit_prices` returns them. Top-up prices are shown only in the app and the Free allowance is stated two ways (15 of 20). A Free plan exists at $0. The Solo plan card is where MCP is listed, and we could not confirm that Free includes it or that signup needs no card (15 of 20). A person signs in through a browser to approve each connection (0). 0 + 15 + 15 + 0 = 30." }, "scores": { "a": 35, "b": 30 } } ], "facts": [ { "a": "HTTP API", "b": "MCP server", "name": "Kind" }, { "a": "Databar, Inc.", "b": "FuseAI, LLC", "name": "Vendor" }, { "a": "https://mcp.databar.ai/mcp", "b": "https://mcp.fuseai.com", "name": "Hosted endpoint" }, { "a": "HTTP, Streamable HTTP, SSE (legacy)", "b": "Streamable HTTP", "name": "Transports" }, { "a": "OAuth or key", "b": "OAuth", "name": "Auth" }, { "a": "Paid", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary, under Databar, Inc.'s terms of service", "b": "Proprietary hosted service under FuseAI's terms of service. No public source repository found", "name": "Licence" }, { "a": "69", "b": "290", "name": "Tools exposed" }, { "a": "no", "b": "yes", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-30", "b": "2026-10-07", "name": "Last release" }, { "a": "2026-10-01", "b": "2026-07-01", "name": "Terms last updated" }, { "a": "2026-10-01", "b": "2026-07-01", "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": "yes", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "yes", "name": "Arbitration or class-action waiver" } ], "faq": [ { "answer": "Databar scores 53.8 (D) on agent readiness against Fuse MCP's 44.3 (E), and leads in 6 of 7 scored categories. Fuse MCP leads on reliability.", "question": "Which is better for AI agents, Databar or Fuse MCP?" }, { "answer": "Databar takes an API key or an OAuth sign-in. Fuse MCP uses an OAuth sign-in.", "question": "Do Databar and Fuse MCP need an API key?" }, { "answer": "Yes. Databar has a hosted endpoint at https://mcp.databar.ai/mcp and Fuse MCP at https://mcp.fuseai.com.", "question": "Can an agent call Databar and Fuse MCP without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 84 against 50", "Agent ergonomics, 66 against 57", "Payments \u0026 pricing, 35 against 30", "Maintenance \u0026 community, 73 against 35" ], "also": [ "Free to start without a card" ], "goodFor": "Waterfall enrichment across many providers for GTM agents, close to clay and fullenrich.", "slug": "databar", "watchFor": "API access needs a paid plan; the free plan's 150 credits don't include it" }, { "aheadOn": [ "Reliability, 40 against 28" ], "also": null, "goodFor": "Suited to a salesperson or founder who wants an assistant to build prospect lists, enrich them and run email and LinkedIn outreach inside one Fuse account.", "slug": "fuse-mcp", "watchFor": "The only OAuth scope is `mcp:tools`, so a connection can do everything its user can, including sending email and LinkedIn messages" } ], "history": { "databar": null, "fuse-mcp": [ { "causes": [ "correction" ], "date": "2026-11-04", "delta": -3.9, "from": 48.2, "fromGrade": "D", "to": 44.3, "toGrade": "E" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.3, "from": 47.9, "fromGrade": "D", "to": 48.2, "toGrade": "D" } ] }, "job": { "capability": "lead.enrichment", "name": "Lead enrichment" }, "others": [ { "json": "https://www.anchorterminal.com/compare/apollo-vs-databar.json", "title": "Apollo API + MCP vs Databar", "url": "https://www.anchorterminal.com/compare/apollo-vs-databar" }, { "json": "https://www.anchorterminal.com/compare/apollo-vs-fuse-mcp.json", "title": "Apollo API + MCP vs Fuse MCP", "url": "https://www.anchorterminal.com/compare/apollo-vs-fuse-mcp" }, { "json": "https://www.anchorterminal.com/compare/clay-vs-databar.json", "title": "Clay vs Databar", "url": "https://www.anchorterminal.com/compare/clay-vs-databar" }, { "json": "https://www.anchorterminal.com/compare/clay-vs-fuse-mcp.json", "title": "Clay vs Fuse MCP", "url": "https://www.anchorterminal.com/compare/clay-vs-fuse-mcp" }, { "json": "https://www.anchorterminal.com/compare/coresignal-vs-databar.json", "title": "Coresignal API + MCP vs Databar", "url": "https://www.anchorterminal.com/compare/coresignal-vs-databar" }, { "json": "https://www.anchorterminal.com/compare/coresignal-vs-fuse-mcp.json", "title": "Coresignal API + MCP vs Fuse MCP", "url": "https://www.anchorterminal.com/compare/coresignal-vs-fuse-mcp" }, { "json": "https://www.anchorterminal.com/compare/crustdata-vs-databar.json", "title": "Crustdata API + MCP vs Databar", "url": "https://www.anchorterminal.com/compare/crustdata-vs-databar" }, { "json": "https://www.anchorterminal.com/compare/crustdata-vs-fuse-mcp.json", "title": "Crustdata API + MCP vs Fuse MCP", "url": "https://www.anchorterminal.com/compare/crustdata-vs-fuse-mcp" }, { "json": "https://www.anchorterminal.com/compare/dievio-vs-fuse-mcp.json", "title": "Dievio vs Fuse MCP", "url": "https://www.anchorterminal.com/compare/dievio-vs-fuse-mcp" }, { "json": "https://www.anchorterminal.com/compare/enrich-layer-vs-fuse-mcp.json", "title": "Enrich Layer API + MCP vs Fuse MCP", "url": "https://www.anchorterminal.com/compare/enrich-layer-vs-fuse-mcp" }, { "json": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-fuse-mcp.json", "title": "Explorium AgentSource vs Fuse MCP", "url": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-fuse-mcp" }, { "json": "https://www.anchorterminal.com/compare/fullenrich-vs-fuse-mcp.json", "title": "FullEnrich API + MCP vs Fuse MCP", "url": "https://www.anchorterminal.com/compare/fullenrich-vs-fuse-mcp" }, { "json": "https://www.anchorterminal.com/compare/fuse-mcp-vs-gojiberry.json", "title": "Fuse MCP vs Gojiberry", "url": "https://www.anchorterminal.com/compare/fuse-mcp-vs-gojiberry" }, { "json": "https://www.anchorterminal.com/compare/fuse-mcp-vs-hunter.json", "title": "Fuse MCP vs Hunter API + MCP", "url": "https://www.anchorterminal.com/compare/fuse-mcp-vs-hunter" }, { "json": "https://www.anchorterminal.com/compare/fuse-mcp-vs-leadmagic.json", "title": "Fuse MCP vs LeadMagic API + MCP", "url": "https://www.anchorterminal.com/compare/fuse-mcp-vs-leadmagic" }, { "json": "https://www.anchorterminal.com/compare/fuse-mcp-vs-lusha.json", "title": "Fuse MCP vs Lusha API + MCP", "url": "https://www.anchorterminal.com/compare/fuse-mcp-vs-lusha" }, { "json": "https://www.anchorterminal.com/compare/fuse-mcp-vs-people-data-labs.json", "title": "Fuse MCP vs People Data Labs", "url": "https://www.anchorterminal.com/compare/fuse-mcp-vs-people-data-labs" }, { "json": "https://www.anchorterminal.com/compare/fuse-mcp-vs-prospeo.json", "title": "Fuse MCP vs Prospeo API + MCP", "url": "https://www.anchorterminal.com/compare/fuse-mcp-vs-prospeo" }, { "json": "https://www.anchorterminal.com/compare/fuse-mcp-vs-rocketreach.json", "title": "Fuse MCP vs RocketReach API", "url": "https://www.anchorterminal.com/compare/fuse-mcp-vs-rocketreach" }, { "json": "https://www.anchorterminal.com/compare/fuse-mcp-vs-zoominfo.json", "title": "Fuse MCP vs ZoomInfo API + MCP", "url": "https://www.anchorterminal.com/compare/fuse-mcp-vs-zoominfo" }, { "json": "https://www.anchorterminal.com/compare/clearbit-vs-databar.json", "title": "Clearbit vs Databar", "url": "https://www.anchorterminal.com/compare/clearbit-vs-databar" }, { "json": "https://www.anchorterminal.com/compare/clearbit-vs-fuse-mcp.json", "title": "Clearbit vs Fuse MCP", "url": "https://www.anchorterminal.com/compare/clearbit-vs-fuse-mcp" }, { "json": "https://www.anchorterminal.com/compare/databar-vs-dievio.json", "title": "Databar vs Dievio", "url": "https://www.anchorterminal.com/compare/databar-vs-dievio" }, { "json": "https://www.anchorterminal.com/compare/databar-vs-dropcontact.json", "title": "Databar vs Dropcontact API + MCP", "url": "https://www.anchorterminal.com/compare/databar-vs-dropcontact" }, { "json": "https://www.anchorterminal.com/compare/databar-vs-enrich-layer.json", "title": "Databar vs Enrich Layer API + MCP", "url": "https://www.anchorterminal.com/compare/databar-vs-enrich-layer" }, { "json": "https://www.anchorterminal.com/compare/databar-vs-explorium-agentsource.json", "title": "Databar vs Explorium AgentSource", "url": "https://www.anchorterminal.com/compare/databar-vs-explorium-agentsource" }, { "json": "https://www.anchorterminal.com/compare/databar-vs-fullcontact.json", "title": "Databar vs FullContact", "url": "https://www.anchorterminal.com/compare/databar-vs-fullcontact" }, { "json": "https://www.anchorterminal.com/compare/databar-vs-fullenrich.json", "title": "Databar vs FullEnrich API + MCP", "url": "https://www.anchorterminal.com/compare/databar-vs-fullenrich" }, { "json": "https://www.anchorterminal.com/compare/databar-vs-gojiberry.json", "title": "Databar vs Gojiberry", "url": "https://www.anchorterminal.com/compare/databar-vs-gojiberry" }, { "json": "https://www.anchorterminal.com/compare/databar-vs-hunter.json", "title": "Databar vs Hunter API + MCP", "url": "https://www.anchorterminal.com/compare/databar-vs-hunter" }, { "json": "https://www.anchorterminal.com/compare/databar-vs-leadmagic.json", "title": "Databar vs LeadMagic API + MCP", "url": "https://www.anchorterminal.com/compare/databar-vs-leadmagic" }, { "json": "https://www.anchorterminal.com/compare/databar-vs-lusha.json", "title": "Databar vs Lusha API + MCP", "url": "https://www.anchorterminal.com/compare/databar-vs-lusha" }, { "json": "https://www.anchorterminal.com/compare/databar-vs-people-data-labs.json", "title": "Databar vs People Data Labs", "url": "https://www.anchorterminal.com/compare/databar-vs-people-data-labs" }, { "json": "https://www.anchorterminal.com/compare/databar-vs-prospeo.json", "title": "Databar vs Prospeo API + MCP", "url": "https://www.anchorterminal.com/compare/databar-vs-prospeo" }, { "json": "https://www.anchorterminal.com/compare/databar-vs-rocketreach.json", "title": "Databar vs RocketReach API", "url": "https://www.anchorterminal.com/compare/databar-vs-rocketreach" }, { "json": "https://www.anchorterminal.com/compare/databar-vs-zerobounce.json", "title": "Databar vs ZeroBounce", "url": "https://www.anchorterminal.com/compare/databar-vs-zerobounce" }, { "json": "https://www.anchorterminal.com/compare/databar-vs-zoominfo.json", "title": "Databar vs ZoomInfo API + MCP", "url": "https://www.anchorterminal.com/compare/databar-vs-zoominfo" }, { "json": "https://www.anchorterminal.com/compare/dropcontact-vs-fuse-mcp.json", "title": "Dropcontact API + MCP vs Fuse MCP", "url": "https://www.anchorterminal.com/compare/dropcontact-vs-fuse-mcp" }, { "json": "https://www.anchorterminal.com/compare/fullcontact-vs-fuse-mcp.json", "title": "FullContact vs Fuse MCP", "url": "https://www.anchorterminal.com/compare/fullcontact-vs-fuse-mcp" }, { "json": "https://www.anchorterminal.com/compare/fuse-mcp-vs-zerobounce.json", "title": "Fuse MCP vs ZeroBounce", "url": "https://www.anchorterminal.com/compare/fuse-mcp-vs-zerobounce" } ], "panel": null, "scores": [ { "by": 12, "databar": 28, "edge": "fuse-mcp", "fuse-mcp": 40, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 34, "databar": 84, "edge": "databar", "fuse-mcp": 50, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 9, "databar": 66, "edge": "databar", "fuse-mcp": 57, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 4, "databar": 47, "edge": "databar", "fuse-mcp": 43, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 5, "databar": 35, "edge": "databar", "fuse-mcp": 30, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 38, "databar": 73, "edge": "databar", "fuse-mcp": 35, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 3, "databar": 55, "edge": "databar", "fuse-mcp": 52, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Databar scores 53.8 (D) on agent readiness against Fuse MCP's 44.3 (E), and leads in 6 of 7 scored categories. Fuse MCP leads on reliability. Both do lead enrichment.", "tasks": null, "tutorials": [], "verdicts": { "databar": "Databar puts 100+ enrichment providers, waterfalls and tables behind one REST API, a Python SDK, a CLI and a hosted MCP server with spending confirmation above 50 credits and stable error codes. API access needs a paid plan or trial, rate limits aren't published as numbers, and no status page or security programme was found.", "fuse-mcp": "The server documents 290 tools with read-only and destructive annotations, OAuth with PKCE and dynamic client registration, and published limits of 60 requests a minute. The single `mcp:tools` scope grants everything the user can do, sends happen at once with no undo, and no status page, changelog or security contact was found." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/databar-vs-fuse-mcp", "json": "https://www.anchorterminal.com/compare/databar-vs-fuse-mcp.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/databar-vs-fuse-mcp.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/databar-vs-fuse-mcp.min.md" }, "markdown": "Databar scores 53.8 (D) on agent readiness against Fuse MCP's 44.3 (E), and leads in 6 of 7 scored categories. Fuse MCP leads on reliability. Both do lead enrichment.\n\n- Databar: grade D, 53.8/100, rank #933 of 1486. Markdown https://www.anchorterminal.com/tools/databar.md · JSON https://www.anchorterminal.com/api/v1/tools/databar.json\n- Fuse MCP: grade E, 44.3/100, rank #1212 of 1486. Markdown https://www.anchorterminal.com/tools/fuse-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/fuse-mcp.json\n- Best lead, contact and company data APIs for AI agents: https://www.anchorterminal.com/best/lead-data/index.md\n- All 231 leads comparisons: https://www.anchorterminal.com/compare/lead-data/index.md\n\n## Which one, for what\n\n### Databar (D)\n\nGood for: Waterfall enrichment across many providers for GTM agents, close to clay and fullenrich.\n\nAhead on:\n- Schema \u0026 documentation, 84 against 50\n- Agent ergonomics, 66 against 57\n- Payments \u0026 pricing, 35 against 30\n- Maintenance \u0026 community, 73 against 35\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: API access needs a paid plan; the free plan's 150 credits don't include it\n\n### Fuse MCP (E)\n\nGood for: Suited to a salesperson or founder who wants an assistant to build prospect lists, enrich them and run email and LinkedIn outreach inside one Fuse account.\n\nAhead on:\n- Reliability, 40 against 28\n\nWatch for: The only OAuth scope is `mcp:tools`, so a connection can do everything its user can, including sending email and LinkedIn messages\n\n\n## Why the edge\n\n### Maintenance \u0026 community: Databar +38\n\n- Databar (73): Closed service. Python SDK 2.9.0 on 30 October 2026, 7 days before this check (30). SDK 2.7.0 and 2.8.0 on 6 October and changelog entries on 23, 24, 27, 28, 29 and 30 September and 1 October (20). A public changelog, roadmap and feedback portal, an email address, and a Slack channel on Scale (10 of 15). An official Python SDK and CLI, no other languages (10 of 15). Package health not checked (3 of 10). 30+20+10+10+3 = 73.\n- Fuse MCP (35): Readings are per the 8 October check, not re-read on 4 November 2026. The tool reference is dated 7 October 2026 and records the October 2026 rebuild of the tool list, within 30 days today (30); it drops to 20 after 6 November unless a newer dated change appears. No changelog or release notes found, so three dated entries in 90 days could not be shown (0). No public changelog or issue tracker. Support is by email at support@fuseai.com, not tested (5 of 15). No readable registry page names the server and no official SDK was found (0). No package to assess (0 of 10). 30 + 0 + 5 + 0 + 0 = 35.\n\n### Schema \u0026 documentation: Databar +34\n\n- Databar (84): Each API reference page embeds its OpenAPI 3.1 operation (spec version 0.1.2), with no downloadable file found (20 of 25). llms.txt with 79 API entries and Markdown twins (10). Descriptions say when to use each endpoint, such as headless runs against table runs, and what a delete leaves behind (16 of 20). Typed request bodies with required fields (12 of 15). An error envelope with stable codes and examples for 400, 406 and 422 (14 of 15). v1 paths and a dated changelog, though the API's own versioning isn't described (12 of 15). 20+10+16+12+14+12 = 84.\n- Fuse MCP (50): Readings are per the 8 October check, not re-read on 4 November 2026, since FuseAI's terms bar automated extraction from its website and docs. Contract line 0 (was 22 of 25). The MCP tool schemas were never read, because tools/list needs a signed-in account, and the docs only say every tool ships one. The 8 October reading leaned on the REST API's OpenAPI file, a separate surface, and no reading records a docs page that shows or links it, so it is struck for this line, as jambonz's and stable-audio's were. llms.txt, Markdown twins of every page and a skill file (10). The tool reference shows descriptions that state purpose, the preferred tool for a job and when a destructive tool may be called (16 of 20). Enum lookup tools such as `get_company_search_enums` exist, but input constraints were not read first-hand (9 of 15). Error results are documented with codes and two JSON examples, plus four plain-text failures, and the docs say the codes do not always match the REST catalogue (12 of 15). No changelog was found and the docs say the server does not announce changes to the tool list. The tool reference is dated 7 October 2026 (3 of 15). 0 + 10 + 16 + 9 + 12 + 3 = 50.\n\n### Reliability: Fuse MCP +12\n\n- Databar (28): Hosted lines. No status page linked from the site or docs (0). No incident history to read (5). The 20 August changelog says rate limits return 429, but no numbers were found in the docs read (5 of 15). The SDK backs off on 429 per the 28 September entry, tasks can be cancelled with a refund, and no Retry-After or idempotency key is documented (8 of 15). No SLA found (0). The MCP server left beta on 15 July 2026 and the API is generally available (10). 0+5+5+8+0+10 = 28.\n- Fuse MCP (40): Graded as a hosted service. FuseAI's terms bar automated systems or scripts from extracting content from the Services, which they define to include the website, so every fuseai.com page keeps its 8 October reading, not re-read on 4 November 2026. No status page is linked from the site, the docs or the sitemap (0). No readable incident history (5). MCP limits are published at 60 requests a minute and 5,000 a day per user (15). The server answers 429 with `RATE_LIMIT_EXCEEDED` and the docs say to back off and retry. No `Retry-After` is documented for the MCP server and there are no idempotency keys, so backoff guidance alone (10). No SLA found (0). The server carries no beta or preview label (10). 0 + 5 + 15 + 10 + 0 + 10 = 40.\n\n### Agent ergonomics: Databar +9\n\n- Databar (66): 69 MCP tools with no toolsets found (5), and REST row reads sized by `per_page` with `has_next_page` (10 of 25 for the two together). Pagination, row filters and a search parameter on enrichments (16 of 20). Errors name the fix, such as unknown columns with the available ones, 406 for credits, 409 for a stale `internal_version` and 410 for expired results (18 of 20). Upserts by key, version tokens on flow edits, cancel with refund, and MCP confirmation above 50 credits; MCP tool annotations not confirmed (13 of 20). Python SDK and a CLI, one language (9 of 15). 10+16+18+13+9 = 66.\n- Fuse MCP (57): Readings are per the 8 October check, not re-read on 4 November 2026. 290 tools and about half a megabyte of definitions, with no toolsets, dynamic loading or read-only subset. The docs warn that some clients pass only the first 40 tools (5 of 25). List reads return a `data` array with `pagination`, searches return a scroll token or cursor, and tools take limits and filters (18 of 20). Rejected calls set `isError` and return codes such as `TOOL_ARGUMENT_VALIDATION_FAILED` with the missing field named. Other failures are short plain text (15 of 20). The docs say every tool carries `readOnlyHint` or `destructiveHint`, which we could not read from the server. No idempotency keys, and sends are not marked destructive (14 of 20). No official SDK found, and most changes need an id looked up first (5 of 15). 5 + 18 + 15 + 14 + 5 = 57.\n\n### Payments \u0026 pricing: Databar +5\n\n- Databar (35): No x402, MPP or L402 (0). Plan prices and credits are public, and each connector's credit cost is shown before a run and in the enrichment's pricing field; credits aren't sold per call outside a plan (15 of 20). A 14-day premium trial with no card, per the pricing FAQ (20). A person signs up in a browser, and API access needs a paid plan (0). 0+15+20+0 = 35.\n- Fuse MCP (30): Readings are per the 8 October check, not re-read on 4 November 2026. No x402, MPP or L402 (0). Plan prices and the credit cost of each action are public, and `get_credit_prices` returns them. Top-up prices are shown only in the app and the Free allowance is stated two ways (15 of 20). A Free plan exists at $0. The Solo plan card is where MCP is listed, and we could not confirm that Free includes it or that signup needs no card (15 of 20). A person signs in through a browser to approve each connection (0). 0 + 15 + 15 + 0 = 30.\n\n## Score by category\n\n| Category | Weight | Databar | Fuse MCP | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 28 | 40 | Fuse MCP +12 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 84 | 50 | Databar +34 |\n| Agent ergonomics | 13% (16.2 this run) | 66 | 57 | Databar +9 |\n| Security \u0026 auth | 14% (17.5 this run) | 47 | 43 | Databar +4 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 35 | 30 | Databar +5 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 73 | 35 | Databar +38 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 55 | 52 | Databar +3 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **53.8 · D** | **44.3 · E** | |\n\n## Facts side by side\n\n| Fact | Databar | Fuse MCP |\n| --- | --- | --- |\n| Kind | HTTP API | MCP server |\n| Vendor | Databar, Inc. | FuseAI, LLC |\n| Hosted endpoint | `https://mcp.databar.ai/mcp` | `https://mcp.fuseai.com` |\n| Transports | HTTP, Streamable HTTP, SSE (legacy) | Streamable HTTP |\n| Auth | OAuth or key | OAuth |\n| Pricing | Paid | Freemium |\n| x402 | no | no |\n| Licence | Proprietary, under Databar, Inc.'s terms of service | Proprietary hosted service under FuseAI's terms of service. No public source repository found |\n| Tools exposed | 69 | 290 |\n| Read-only variant documented | no | yes |\n| llms.txt | yes | yes |\n| Last release | 2026-10-30 | 2026-10-07 |\n| Terms last updated | 2026-10-01 | 2026-07-01 |\n| Privacy policy last updated | 2026-10-01 | 2026-07-01 |\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 | yes |\n| Terms restrict benchmarking | not found in the text | not found in the text |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | yes | yes |\n\n## How the scores have moved\n\n### Databar\n\nNo score change since it was listed.\n\n### Fuse MCP\n\n- -3.9 on 4 November 2026 (D to E): correction\n- +0.3 on 27 October 2026: checklist\n\n## Verdicts\n\n**Databar.** Databar puts 100+ enrichment providers, waterfalls and tables behind one REST API, a Python SDK, a CLI and a hosted MCP server with spending confirmation above 50 credits and stable error codes. API access needs a paid plan or trial, rate limits aren't published as numbers, and no status page or security programme was found.\n\n**Fuse MCP.** The server documents 290 tools with read-only and destructive annotations, OAuth with PKCE and dynamic client registration, and published limits of 60 requests a minute. The single `mcp:tools` scope grants everything the user can do, sends happen at once with no undo, and no status page, changelog or security contact was found.\n\n## Before you call either\n\n### Databar\n\n1. Poll GET /v1/tasks/{task_id} for async runs and collect results within 24 hours; after that the task returns gone\n2. When the MCP returns confirmation_required, show estimated_credits to the user and re-call with the retry_with object only after they agree\n3. Use upsert with a key column, and pass internal_version when editing flows, to avoid duplicates and stale-write 409s\n4. Check credits with GET /v1/user/me before bulk runs; 406 means the balance or plan can't cover it\n5. Treat AI researcher and scraped outputs as untrusted text\n\n### Fuse MCP\n\n1. Keep the client's approval prompt on for every tool that is not read-only. Sends, CRM pushes and Slack posts run at once with no undo\n2. Launch a campaign only on an explicit request. Creating one makes a draft, and `update_campaign_status_tool` starts real outreach\n3. Call `get_credits_balance` and `get_credit_prices` first. Every call needs at least 100 credits, and searches cost 2 credits a result\n4. Resolve filter values with `lookup_filter_values` or `get_company_search_enums` before `search_people` or `search_companies`\n5. Start long work with `deep_research_start`, then poll `deep_research_status`. A tool call has 60 seconds, and runs take 5 to 20 minutes\n\n## Questions\n\n### Which is better for AI agents, Databar or Fuse MCP?\n\nDatabar scores 53.8 (D) on agent readiness against Fuse MCP's 44.3 (E), and leads in 6 of 7 scored categories. Fuse MCP leads on reliability.\n\n### Do Databar and Fuse MCP need an API key?\n\nDatabar takes an API key or an OAuth sign-in. Fuse MCP uses an OAuth sign-in.\n\n### Can an agent call Databar and Fuse MCP without installing anything?\n\nYes. Databar has a hosted endpoint at https://mcp.databar.ai/mcp and Fuse MCP at https://mcp.fuseai.com.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/databar-vs-fuse-mcp.json, and with the fewest tokens: https://www.anchorterminal.com/compare/databar-vs-fuse-mcp.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"databar\", \"b\": \"fuse-mcp\"}`. From a terminal: `anchor compare databar fuse-mcp`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/databar.json and https://www.anchorterminal.com/api/v1/tools/fuse-mcp.json\n\n## Other comparisons with Databar or Fuse MCP\n\n- [Apollo API + MCP vs Databar](https://www.anchorterminal.com/compare/apollo-vs-databar.md)\n- [Apollo API + MCP vs Fuse MCP](https://www.anchorterminal.com/compare/apollo-vs-fuse-mcp.md)\n- [Clay vs Databar](https://www.anchorterminal.com/compare/clay-vs-databar.md)\n- [Clay vs Fuse MCP](https://www.anchorterminal.com/compare/clay-vs-fuse-mcp.md)\n- [Coresignal API + MCP vs Databar](https://www.anchorterminal.com/compare/coresignal-vs-databar.md)\n- [Coresignal API + MCP vs Fuse MCP](https://www.anchorterminal.com/compare/coresignal-vs-fuse-mcp.md)\n- [Crustdata API + MCP vs Databar](https://www.anchorterminal.com/compare/crustdata-vs-databar.md)\n- [Crustdata API + MCP vs Fuse MCP](https://www.anchorterminal.com/compare/crustdata-vs-fuse-mcp.md)\n- [Dievio vs Fuse MCP](https://www.anchorterminal.com/compare/dievio-vs-fuse-mcp.md)\n- [Enrich Layer API + MCP vs Fuse MCP](https://www.anchorterminal.com/compare/enrich-layer-vs-fuse-mcp.md)\n- [Explorium AgentSource vs Fuse MCP](https://www.anchorterminal.com/compare/explorium-agentsource-vs-fuse-mcp.md)\n- [FullEnrich API + MCP vs Fuse MCP](https://www.anchorterminal.com/compare/fullenrich-vs-fuse-mcp.md)\n- [Fuse MCP vs Gojiberry](https://www.anchorterminal.com/compare/fuse-mcp-vs-gojiberry.md)\n- [Fuse MCP vs Hunter API + MCP](https://www.anchorterminal.com/compare/fuse-mcp-vs-hunter.md)\n- [Fuse MCP vs LeadMagic API + MCP](https://www.anchorterminal.com/compare/fuse-mcp-vs-leadmagic.md)\n- [Fuse MCP vs Lusha API + MCP](https://www.anchorterminal.com/compare/fuse-mcp-vs-lusha.md)\n- [Fuse MCP vs People Data Labs](https://www.anchorterminal.com/compare/fuse-mcp-vs-people-data-labs.md)\n- [Fuse MCP vs Prospeo API + MCP](https://www.anchorterminal.com/compare/fuse-mcp-vs-prospeo.md)\n- [Fuse MCP vs RocketReach API](https://www.anchorterminal.com/compare/fuse-mcp-vs-rocketreach.md)\n- [Fuse MCP vs ZoomInfo API + MCP](https://www.anchorterminal.com/compare/fuse-mcp-vs-zoominfo.md)\n- [Clearbit vs Databar](https://www.anchorterminal.com/compare/clearbit-vs-databar.md)\n- [Clearbit vs Fuse MCP](https://www.anchorterminal.com/compare/clearbit-vs-fuse-mcp.md)\n- [Databar vs Dievio](https://www.anchorterminal.com/compare/databar-vs-dievio.md)\n- [Databar vs Dropcontact API + MCP](https://www.anchorterminal.com/compare/databar-vs-dropcontact.md)\n- [Databar vs Enrich Layer API + MCP](https://www.anchorterminal.com/compare/databar-vs-enrich-layer.md)\n- [Databar vs Explorium AgentSource](https://www.anchorterminal.com/compare/databar-vs-explorium-agentsource.md)\n- [Databar vs FullContact](https://www.anchorterminal.com/compare/databar-vs-fullcontact.md)\n- [Databar vs FullEnrich API + MCP](https://www.anchorterminal.com/compare/databar-vs-fullenrich.md)\n- [Databar vs Gojiberry](https://www.anchorterminal.com/compare/databar-vs-gojiberry.md)\n- [Databar vs Hunter API + MCP](https://www.anchorterminal.com/compare/databar-vs-hunter.md)\n- [Databar vs LeadMagic API + MCP](https://www.anchorterminal.com/compare/databar-vs-leadmagic.md)\n- [Databar vs Lusha API + MCP](https://www.anchorterminal.com/compare/databar-vs-lusha.md)\n- [Databar vs People Data Labs](https://www.anchorterminal.com/compare/databar-vs-people-data-labs.md)\n- [Databar vs Prospeo API + MCP](https://www.anchorterminal.com/compare/databar-vs-prospeo.md)\n- [Databar vs RocketReach API](https://www.anchorterminal.com/compare/databar-vs-rocketreach.md)\n- [Databar vs ZeroBounce](https://www.anchorterminal.com/compare/databar-vs-zerobounce.md)\n- [Databar vs ZoomInfo API + MCP](https://www.anchorterminal.com/compare/databar-vs-zoominfo.md)\n- [Dropcontact API + MCP vs Fuse MCP](https://www.anchorterminal.com/compare/dropcontact-vs-fuse-mcp.md)\n- [FullContact vs Fuse MCP](https://www.anchorterminal.com/compare/fullcontact-vs-fuse-mcp.md)\n- [Fuse MCP vs ZeroBounce](https://www.anchorterminal.com/compare/fuse-mcp-vs-zerobounce.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": "2026-11-07", "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": "Databar vs Fuse MCP", "url": "" } ], "description": "Databar scores 53.8 (D) to Fuse MCP's 44.3 (E) for lead enrichment. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Databar D 53.8", "Fuse MCP E 44.3", "scores" ], "h1": "Databar vs Fuse MCP", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/databar-vs-fuse-mcp", "published": "2026-10-01", "section": "tools", "title": "Databar vs Fuse MCP for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/databar-vs-fuse-mcp" }, "tokens": { "markdown": 4500, "slim": 2280 }, "version": 1 }