{ "data": { "a": { "slug": "explorium-agentsource", "name": "Explorium AgentSource", "vendor": "Explorium Ltd.", "vendorUrl": "https://www.explorium.ai", "kind": "http-api", "category": "lead-data", "summary": "Explorium's AgentSource is a B2B data service for matching, searching and enriching companies and prospects, with event signals and AI research tasks. Agents reach it through a REST API (v2) and a hosted MCP server.", "url": "https://www.anchorterminal.com/tools/explorium-agentsource", "markdownUrl": "https://www.anchorterminal.com/tools/explorium-agentsource.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/explorium-agentsource.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/explorium-agentsource.json", "repo": "https://github.com/explorium-ai/mcp-explorium", "license": "Proprietary service under the Explorium Terms of Use. The `mcp-explorium` repository of connection files is MIT", "transports": [ "http", "streamable-http", "sse" ], "remoteUrl": "https://api.explorium.ai", "packages": [], "auth": "api-key", "authNotes": "Self-serve API key from the admin console at admin.explorium.ai, sent in the `api_key` header. The docs say each company gets one key shared by all its users, with no scopes. The MCP v2 guide sends the same key as `Authorization: Bearer`. The older v1 MCP server at `mcp.explorium.ai` uses OAuth. The vendor's `auth.md` says registration needs a person and there is no client-registration endpoint.", "pricing": "usage", "pricingNotes": "One-off credit packs, no subscription. The pricing page lists Lite $29.99 for 500 credits, Starter $149.99 for 5,000, Growth $749.99 for 30,000 and Scale $7,499.99 for 500,000, valid 12 months and non-refundable. A free trial gives 100 credits for 90 days, so an agent's owner can start without a contract. The site's `pricing.md` (dated 26 August 2026) lists Starter at $99.99 for 2,500 and Growth at 25,000 credits instead. Fetch costs 1 credit a result (2 with the Bombora intent filter), enrichments 1 to 5, and contact enrichment 2 for email or 5 with phone.", "priceSummary": "$0.06 / credit", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs index, the OpenAPI file, the pricing files or the terms of use (checked 2026-10-09).", "endpoints": [] }, "toolCount": 11, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-09" }, "docsUrl": "https://developers.explorium.ai", "llmsTxt": "https://developers.explorium.ai/llms.txt", "openapi": "https://developers.explorium.ai/openapi.json", "capabilities": [ "lead.search", "lead.enrichment", "email.finder", "data.company", "data.person" ], "tags": [ "lead-search", "enrichment", "hosted", "mcp", "openapi", "llms-txt", "webhooks", "async-jobs", "credits", "free-trial", "closed-source" ], "lastRelease": "2026-09-02", "graded": true, "anchor": { "graded": true, "score": 48.1, "grade": "D", "agentReady": false, "rank": 821, "ranked": true, "rankOf": 950, "categoryRank": 14, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 63, "maintenance": 28, "payments": 40, "reliability": 42, "schema": 76, "security": 37, "transparency": 59 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-09" }, "negative": -2, "negativeNotes": [ "On 9 October 2026 the site's machine-readable `pricing.md` (dated 26 August 2026) lists Starter at $99.99 for 2,500 credits and Growth at 25,000 credits, while the pricing page it names as canonical lists $149.99 for 5,000 and 30,000. The site's `auth.md` and server card also send agents to the MCP server the docs call deprecated. A misleading published claim, 2 points (https://www.explorium.ai/pricing.md, https://www.explorium.ai/pricing/)" ], "verdict": "AgentSource v2 has a public OpenAPI 3.1 file, Markdown docs, a 200 queries a minute limit with `Retry-After`, public credit prices and a 100-credit trial. No status page or published SLA was found, each company shares one API key with no scopes, and the vendor's two published price tables disagree.", "bestFor": "Agents that build prospect lists by filter and then enrich them, or that watch companies for events such as funding and role changes.", "strengths": [ "Public OpenAPI 3.1 file covering 74 v2 operations, plus llms.txt and a Markdown twin of every docs page", "Rate limit of 200 queries a minute per key, with `X-RateLimit-*` headers and `Retry-After` on 429", "Credit packs priced in public from $0.015 to $0.06 a credit, and a 100-credit free trial valid 90 days", "Statistics endpoints are free, and the `credit-usage: true` header returns the credits each call spent", "v1 retirement timeline published, with end of support about six months and retirement about twelve months after 2 September 2026" ], "weaknesses": [ "No status page was found, and no SLA is published", "One API key per company, shared by all users, with no scopes or read-only mode", "The site's `pricing.md` and its pricing page give different prices for the Starter and Growth packs", "The terms of use bar benchmarking and automated data collection, and allow service changes without notice", "No dated changelog and no official REST SDK found in the docs index" ], "agentNotes": [ "Send the key in the `api_key` header to `https://api.explorium.ai` and use `/v2` paths. v1 is deprecated", "Point MCP clients at `https://mcp-v2.explorium.ai/mcp`. The site's agent files still name the v1 server at `mcp.explorium.ai`", "Count each entity in a batch as one query against the 200 a minute limit, so 50 IDs in one call spend 50", "Call the statistics endpoint first to size an audience for free. Fetch costs 1 credit a result, or 2 with the Bombora intent filter", "Call `/v2/autocomplete` before filtering on category, tech stack or job title, and never mix two category types in one request" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 48.1 } ], "editorialScores": { "ergonomics": 63, "maintenance": 28, "payments": 40, "reliability": 42, "schema": 76, "security": 37, "transparency": 49 }, "provenanceScore": 68 }, "connect": { "http": "curl --request POST --url https://api.explorium.ai/v1/prospects --header 'accept: application/json' --header 'api_key: YOUR_API_KEY' --header 'content-type: application/json' --data '{\"mode\": \"full\", \"page\": 1}'" }, "letme": { "capability": "https://letme.dev/lead.search", "tool": "https://letme.dev/explorium-agentsource" }, "area": "web-data", "unitPrices": [ { "item": "Lite credit pack", "unit": "credit", "usd": 0.06, "note": "$29.99 for 500 credits, valid 12 months" }, { "item": "Starter credit pack", "unit": "credit", "usd": 0.03, "note": "$149.99 for 5,000 credits on the pricing page. The site's pricing.md says $99.99 for 2,500" }, { "item": "Growth credit pack", "unit": "credit", "usd": 0.025, "note": "$749.99 for 30,000 credits on the pricing page. The site's pricing.md says 25,000" }, { "item": "Scale credit pack", "unit": "credit", "usd": 0.015, "note": "$7,499.99 for 500,000 credits" }, { "item": "Fetched business or prospect", "unit": "record", "usd": 0.03, "note": "1 credit a result at the Starter rate, 2 credits with the Bombora intent filter" }, { "item": "Contact enrichment, email and phone", "unit": "record", "usd": 0.15, "note": "5 credits at the Starter rate. Email only is 2 credits" } ], "provenance": { "legalEntity": "Explorium Ltd.", "domain": "explorium.ai", "domainRegistered": "2018-08-16", "endpointOnVendorDomain": true, "terms": "https://www.explorium.ai/explorium-website-terms-of-use/", "privacy": "https://www.explorium.ai/privacy-policy/", "statusPage": "", "changelog": "https://developers.explorium.ai/v2/whats-new", "securityTxt": "none", "checked": "2026-10-09", "notes": [ "The page at /explorium-website-terms-of-use/ is titled Explorium Terms of Use (updated 14 June 2026). It is a contract between Explorium Ltd. and its affiliates and the customer, and covers the Platform, the API and Platform Data, so it governs the product and not only the website.", "The privacy policy (updated 28 June 2026) names Explorium Ltd., 3 Daniel Frisch St., Tel-Aviv, Israel, and covers the Platform and its end users. The terms give a contact address for Explorium Inc., 400 Concar Drive, San Mateo, California.", "www.explorium.ai/.well-known/security.txt returns the site's page-not-found page.", "No status page is linked from the docs or the site files read. status.explorium.ai did not answer our request.", "The changelog link is the v2 change list. No dated changelog was found in the docs index.", "RDAP for explorium.ai gives a registration date of 2018-08-16.", "The API answers at api.explorium.ai and the MCP server at mcp-v2.explorium.ai." ], "score": 68 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/explorium-agentsource.json", "live": { "slug": "explorium-agentsource", "probe": { "target": "https://api.explorium.ai", "method": "get", "lastAt": "2026-10-10T02:07:08.507066981Z", "lastOk": true, "lastStatus": 401, "lastMs": 152, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 411, "p95ms24h": 1390, "samples24h": 107, "samples30d": 107, "days": [ { "date": "2026-10-09", "probes": 85, "ok": 85 }, { "date": "2026-10-10", "probes": 22, "ok": 22 } ] }, "versions": [ { "registry": "github", "name": "explorium-ai/mcp-explorium", "version": "1.0.0", "released": "2025-09-16", "seenAt": "2026-10-09T16:52:27.476335726Z" } ], "githubStars": 21, "pages": [ { "url": "https://developers.explorium.ai/v2/whats-new", "kind": "changelog", "status": 200, "checkedAt": "2026-10-09T18:35:39.888809319Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "cbf94b2cb520" }, { "url": "https://www.explorium.ai/privacy-policy/", "kind": "privacy", "status": 200, "checkedAt": "2026-10-09T18:50:02.46808686Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "a2cefae01442" }, { "url": "https://www.explorium.ai/explorium-website-terms-of-use/", "kind": "terms", "status": 200, "checkedAt": "2026-10-09T18:49:59.834810876Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "0267ad357a07" } ], "updatedAt": "2026-10-10T02:07:08.507066981Z" } }, "answer": "Explorium AgentSource and Fuse MCP score within a point of each other on agent readiness, 48.1 (D) and 47.9 (D). Fuse MCP leads on security \u0026 auth and maintenance \u0026 community.", "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", "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": 47.9, "grade": "D", "agentReady": false, "rank": 824, "ranked": true, "rankOf": 950, "categoryRank": 15, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 57, "maintenance": 35, "payments": 30, "reliability": 40, "schema": 72, "security": 45, "transparency": 49 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "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 docs, a skill file and an OpenAPI 3.1 spec with 146 operations for the REST API beside it" ], "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": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 47.9 } ], "editorialScores": { "ergonomics": 57, "maintenance": 35, "payments": 30, "reliability": 40, "schema": 72, "security": 45, "transparency": 36 }, "provenanceScore": 62 }, "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": 62 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/fuse-mcp.json", "live": { "slug": "fuse-mcp", "probe": { "target": "https://mcp.fuseai.com", "method": "mcp-initialize", "lastAt": "2026-10-10T02:07:09.614956205Z", "lastOk": true, "lastStatus": 401, "lastMs": 326, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 336, "p95ms24h": 397, "samples24h": 250, "samples30d": 365, "days": [ { "date": "2026-10-08", "probes": 93, "ok": 93 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 22, "ok": 22 } ] }, "securityTxt": { "url": "https://fuseai.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-09T15:39:32.43595019Z" }, "llmsTxt": { "url": "https://docs.fuseai.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-09T14:01:59.6206507Z" }, "pages": [ { "url": "https://fuseai.com/pricing", "kind": "pricing", "status": 304, "checkedAt": "2026-10-09T18:39:47.430628764Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "21fee727aa20" }, { "url": "https://fuseai.com/legal/privacy-policy", "kind": "privacy", "status": 304, "checkedAt": "2026-10-09T18:39:43.211133921Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "d35ecd9cf6d0" }, { "url": "https://fuseai.com/legal/terms-of-service", "kind": "terms", "status": 304, "checkedAt": "2026-10-09T18:39:45.469792858Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "911a898c524d" } ], "mcpTools": { "url": "https://mcp.fuseai.com", "checkedAt": "2026-10-09T21:40:43.594766147Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-10-08T21:33:51.293613327Z" }, "updatedAt": "2026-10-10T02:07:09.614956205Z" } }, "facts": [ { "a": "HTTP API", "b": "MCP server", "name": "Kind" }, { "a": "Explorium Ltd.", "b": "FuseAI, LLC", "name": "Vendor" }, { "a": "https://api.explorium.ai", "b": "https://mcp.fuseai.com", "name": "Hosted endpoint" }, { "a": "HTTP, Streamable HTTP, SSE (legacy)", "b": "Streamable HTTP", "name": "Transports" }, { "a": "API key", "b": "OAuth", "name": "Auth" }, { "a": "Pay per use", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under the Explorium Terms of Use. The `mcp-explorium` repository of connection files is MIT", "b": "Proprietary hosted service under FuseAI's terms of service. No public source repository found", "name": "Licence" }, { "a": "11", "b": "290", "name": "Tools exposed" }, { "a": "no", "b": "yes", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-09-02", "b": "2026-10-07", "name": "Last release" }, { "a": "2026-06-14", "b": "2026-07-01", "name": "Terms last updated" }, { "a": "2026-06-28", "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": "yes", "b": "yes", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "yes", "name": "Arbitration or class-action waiver" } ], "faq": [ { "answer": "Explorium AgentSource and Fuse MCP score within a point of each other on agent readiness, 48.1 (D) and 47.9 (D). Fuse MCP leads on security \u0026 auth and maintenance \u0026 community.", "question": "Which is better for AI agents, Explorium AgentSource or Fuse MCP?" }, { "answer": "Explorium AgentSource needs an API key. Fuse MCP uses an OAuth sign-in.", "question": "Do Explorium AgentSource and Fuse MCP need an API key?" }, { "answer": "Yes. Explorium AgentSource has a hosted endpoint at https://api.explorium.ai and Fuse MCP at https://mcp.fuseai.com.", "question": "Can an agent call Explorium AgentSource and Fuse MCP without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Agent ergonomics, 63 against 57", "Payments \u0026 pricing, 40 against 30", "Transparency \u0026 trust, 59 against 49" ], "also": null, "goodFor": "Agents that build prospect lists by filter and then enrich them, or that watch companies for events such as funding and role changes.", "slug": "explorium-agentsource", "watchFor": "No status page was found, and no SLA is published" }, { "aheadOn": [ "Security \u0026 auth, 45 against 37", "Maintenance \u0026 community, 35 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" } ], "job": { "capability": "lead.search", "name": "Lead search" }, "others": [ { "json": "https://www.anchorterminal.com/compare/apollo-vs-explorium-agentsource.json", "title": "Apollo API + MCP vs Explorium AgentSource", "url": "https://www.anchorterminal.com/compare/apollo-vs-explorium-agentsource" }, { "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/coresignal-vs-explorium-agentsource.json", "title": "Coresignal API + MCP vs Explorium AgentSource", "url": "https://www.anchorterminal.com/compare/coresignal-vs-explorium-agentsource" }, { "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-explorium-agentsource.json", "title": "Crustdata API + MCP vs Explorium AgentSource", "url": "https://www.anchorterminal.com/compare/crustdata-vs-explorium-agentsource" }, { "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/enrich-layer-vs-explorium-agentsource.json", "title": "Enrich Layer API + MCP vs Explorium AgentSource", "url": "https://www.anchorterminal.com/compare/enrich-layer-vs-explorium-agentsource" }, { "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-fullenrich.json", "title": "Explorium AgentSource vs FullEnrich API + MCP", "url": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-fullenrich" }, { "json": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-gojiberry.json", "title": "Explorium AgentSource vs Gojiberry", "url": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-gojiberry" }, { "json": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-hunter.json", "title": "Explorium AgentSource vs Hunter API + MCP", "url": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-hunter" }, { "json": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-leadmagic.json", "title": "Explorium AgentSource vs LeadMagic API + MCP", "url": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-leadmagic" }, { "json": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-lusha.json", "title": "Explorium AgentSource vs Lusha API + MCP", "url": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-lusha" }, { "json": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-people-data-labs.json", "title": "Explorium AgentSource vs People Data Labs", "url": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-people-data-labs" }, { "json": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-prospeo.json", "title": "Explorium AgentSource vs Prospeo API + MCP", "url": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-prospeo" }, { "json": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-rocketreach.json", "title": "Explorium AgentSource vs RocketReach API", "url": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-rocketreach" }, { "json": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-zoominfo.json", "title": "Explorium AgentSource vs ZoomInfo API + MCP", "url": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-zoominfo" }, { "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/dropcontact-vs-explorium-agentsource.json", "title": "Dropcontact API + MCP vs Explorium AgentSource", "url": "https://www.anchorterminal.com/compare/dropcontact-vs-explorium-agentsource" }, { "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" } ], "scores": [ { "by": 2, "edge": "explorium-agentsource", "explorium-agentsource": 42, "fuse-mcp": 40, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 4, "edge": "explorium-agentsource", "explorium-agentsource": 76, "fuse-mcp": 72, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 6, "edge": "explorium-agentsource", "explorium-agentsource": 63, "fuse-mcp": 57, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 8, "edge": "fuse-mcp", "explorium-agentsource": 37, "fuse-mcp": 45, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 10, "edge": "explorium-agentsource", "explorium-agentsource": 40, "fuse-mcp": 30, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 7, "edge": "fuse-mcp", "explorium-agentsource": 28, "fuse-mcp": 35, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 10, "edge": "explorium-agentsource", "explorium-agentsource": 59, "fuse-mcp": 49, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Explorium AgentSource and Fuse MCP score within a point of each other on agent readiness, 48.1 (D) and 47.9 (D). Fuse MCP leads on security \u0026 auth and maintenance \u0026 community. Both do lead search.", "verdicts": { "explorium-agentsource": "AgentSource v2 has a public OpenAPI 3.1 file, Markdown docs, a 200 queries a minute limit with `Retry-After`, public credit prices and a 100-credit trial. No status page or published SLA was found, each company shares one API key with no scopes, and the vendor's two published price tables disagree.", "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/explorium-agentsource-vs-fuse-mcp", "json": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-fuse-mcp.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-fuse-mcp.md", "slim": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-fuse-mcp.min.md" }, "markdown": "Explorium AgentSource and Fuse MCP score within a point of each other on agent readiness, 48.1 (D) and 47.9 (D). Fuse MCP leads on security \u0026 auth and maintenance \u0026 community. Both do lead search.\n\n- Explorium AgentSource: grade D, 48.1/100, rank #821 of 950. Markdown https://www.anchorterminal.com/tools/explorium-agentsource.md · JSON https://www.anchorterminal.com/api/v1/tools/explorium-agentsource.json\n- Fuse MCP: grade D, 47.9/100, rank #824 of 950. 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 120 leads comparisons: https://www.anchorterminal.com/compare/lead-data/index.md\n\n## Which one, for what\n\n### Explorium AgentSource (D)\n\nGood for: Agents that build prospect lists by filter and then enrich them, or that watch companies for events such as funding and role changes.\n\nAhead on:\n- Agent ergonomics, 63 against 57\n- Payments \u0026 pricing, 40 against 30\n- Transparency \u0026 trust, 59 against 49\n\nWatch for: No status page was found, and no SLA is published\n\n### Fuse MCP (D)\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- Security \u0026 auth, 45 against 37\n- Maintenance \u0026 community, 35 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## Score by category\n\n| Category | Weight | Explorium AgentSource | Fuse MCP | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 42 | 40 | Explorium AgentSource +2 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 76 | 72 | Explorium AgentSource +4 |\n| Agent ergonomics | 13% (16.2 this run) | 63 | 57 | Explorium AgentSource +6 |\n| Security \u0026 auth | 14% (17.5 this run) | 37 | 45 | Fuse MCP +8 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 30 | Explorium AgentSource +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 28 | 35 | Fuse MCP +7 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 59 | 49 | Explorium AgentSource +10 |\n| Negative events | ≤15 | -2 | 0 | |\n| **Total** | | **48.1 · D** | **47.9 · D** | |\n\n## Facts side by side\n\n| Fact | Explorium AgentSource | Fuse MCP |\n| --- | --- | --- |\n| Kind | HTTP API | MCP server |\n| Vendor | Explorium Ltd. | FuseAI, LLC |\n| Hosted endpoint | `https://api.explorium.ai` | `https://mcp.fuseai.com` |\n| Transports | HTTP, Streamable HTTP, SSE (legacy) | Streamable HTTP |\n| Auth | API key | OAuth |\n| Pricing | Pay per use | Freemium |\n| x402 | no | no |\n| Licence | Proprietary service under the Explorium Terms of Use. The `mcp-explorium` repository of connection files is MIT | Proprietary hosted service under FuseAI's terms of service. No public source repository found |\n| Tools exposed | 11 | 290 |\n| Read-only variant documented | no | yes |\n| llms.txt | yes | yes |\n| Last release | 2026-09-02 | 2026-10-07 |\n| Terms last updated | 2026-06-14 | 2026-07-01 |\n| Privacy policy last updated | 2026-06-28 | 2026-07-01 |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | yes | yes |\n| Terms restrict benchmarking | yes | not found in the text |\n| Terms or service can change without notice | yes | not found in the text |\n| Arbitration or class-action waiver | not found in the text | yes |\n\n## Verdicts\n\n**Explorium AgentSource.** AgentSource v2 has a public OpenAPI 3.1 file, Markdown docs, a 200 queries a minute limit with `Retry-After`, public credit prices and a 100-credit trial. No status page or published SLA was found, each company shares one API key with no scopes, and the vendor's two published price tables disagree.\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### Explorium AgentSource\n\n1. Send the key in the `api_key` header to `https://api.explorium.ai` and use `/v2` paths. v1 is deprecated\n2. Point MCP clients at `https://mcp-v2.explorium.ai/mcp`. The site's agent files still name the v1 server at `mcp.explorium.ai`\n3. Count each entity in a batch as one query against the 200 a minute limit, so 50 IDs in one call spend 50\n4. Call the statistics endpoint first to size an audience for free. Fetch costs 1 credit a result, or 2 with the Bombora intent filter\n5. Call `/v2/autocomplete` before filtering on category, tech stack or job title, and never mix two category types in one request\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, Explorium AgentSource or Fuse MCP?\n\nExplorium AgentSource and Fuse MCP score within a point of each other on agent readiness, 48.1 (D) and 47.9 (D). Fuse MCP leads on security \u0026 auth and maintenance \u0026 community.\n\n### Do Explorium AgentSource and Fuse MCP need an API key?\n\nExplorium AgentSource needs an API key. Fuse MCP uses an OAuth sign-in.\n\n### Can an agent call Explorium AgentSource and Fuse MCP without installing anything?\n\nYes. Explorium AgentSource has a hosted endpoint at https://api.explorium.ai and Fuse MCP at https://mcp.fuseai.com.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/explorium-agentsource-vs-fuse-mcp.json, and with the fewest tokens: https://www.anchorterminal.com/compare/explorium-agentsource-vs-fuse-mcp.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"explorium-agentsource\", \"b\": \"fuse-mcp\"}`. From a terminal: `anchor compare explorium-agentsource fuse-mcp`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/explorium-agentsource.json and https://www.anchorterminal.com/api/v1/tools/fuse-mcp.json\n\n## Other comparisons with Explorium AgentSource or Fuse MCP\n\n- [Apollo API + MCP vs Explorium AgentSource](https://www.anchorterminal.com/compare/apollo-vs-explorium-agentsource.md)\n- [Apollo API + MCP vs Fuse MCP](https://www.anchorterminal.com/compare/apollo-vs-fuse-mcp.md)\n- [Coresignal API + MCP vs Explorium AgentSource](https://www.anchorterminal.com/compare/coresignal-vs-explorium-agentsource.md)\n- [Coresignal API + MCP vs Fuse MCP](https://www.anchorterminal.com/compare/coresignal-vs-fuse-mcp.md)\n- [Crustdata API + MCP vs Explorium AgentSource](https://www.anchorterminal.com/compare/crustdata-vs-explorium-agentsource.md)\n- [Crustdata API + MCP vs Fuse MCP](https://www.anchorterminal.com/compare/crustdata-vs-fuse-mcp.md)\n- [Enrich Layer API + MCP vs Explorium AgentSource](https://www.anchorterminal.com/compare/enrich-layer-vs-explorium-agentsource.md)\n- [Enrich Layer API + MCP vs Fuse MCP](https://www.anchorterminal.com/compare/enrich-layer-vs-fuse-mcp.md)\n- [Explorium AgentSource vs FullEnrich API + MCP](https://www.anchorterminal.com/compare/explorium-agentsource-vs-fullenrich.md)\n- [Explorium AgentSource vs Gojiberry](https://www.anchorterminal.com/compare/explorium-agentsource-vs-gojiberry.md)\n- [Explorium AgentSource vs Hunter API + MCP](https://www.anchorterminal.com/compare/explorium-agentsource-vs-hunter.md)\n- [Explorium AgentSource vs LeadMagic API + MCP](https://www.anchorterminal.com/compare/explorium-agentsource-vs-leadmagic.md)\n- [Explorium AgentSource vs Lusha API + MCP](https://www.anchorterminal.com/compare/explorium-agentsource-vs-lusha.md)\n- [Explorium AgentSource vs People Data Labs](https://www.anchorterminal.com/compare/explorium-agentsource-vs-people-data-labs.md)\n- [Explorium AgentSource vs Prospeo API + MCP](https://www.anchorterminal.com/compare/explorium-agentsource-vs-prospeo.md)\n- [Explorium AgentSource vs RocketReach API](https://www.anchorterminal.com/compare/explorium-agentsource-vs-rocketreach.md)\n- [Explorium AgentSource vs ZoomInfo API + MCP](https://www.anchorterminal.com/compare/explorium-agentsource-vs-zoominfo.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- [Dropcontact API + MCP vs Explorium AgentSource](https://www.anchorterminal.com/compare/dropcontact-vs-explorium-agentsource.md)\n- [Dropcontact API + MCP vs Fuse MCP](https://www.anchorterminal.com/compare/dropcontact-vs-fuse-mcp.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-10", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Explorium AgentSource vs Fuse MCP", "url": "" } ], "description": "Explorium AgentSource and Fuse MCP score within a point of each other for lead search, 48.1 and 47.9 out of 100. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Explorium AgentSource D 48.1", "Fuse MCP D 47.9", "scores" ], "h1": "Explorium AgentSource vs Fuse MCP", "image": "https://www.anchorterminal.com/assets/og/compare-explorium-agentsource-vs-fuse-mcp.png", "path": "/compare/explorium-agentsource-vs-fuse-mcp", "published": "2026-10-01", "section": "tools", "title": "Explorium AgentSource vs Fuse MCP for AI agents (2026)", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/explorium-agentsource-vs-fuse-mcp" }, "tokens": { "markdown": 2700, "slim": 680 }, "version": 1 }