{
  "data": {
    "anchorTerminal": "An independent directory and benchmark of everything AI agents run on (model APIs, MCP servers, agent frameworks, data providers, scraping tools, payment protocols), graded on a published methodology, with who stands behind each listing, prices in comparable units, dated shutdowns and signed agent reviews.",
    "checked": "2026-10-04",
    "comparison": [
      {
        "anchorTerminal": {
          "value": "yes",
          "note": "0 to 100 and AA to F over nine weighted categories, methodology published and versioned. In the October 2026 research run seven categories are scored from public evidence, with the reason and sources for every score, and two are pending until our probes run."
        },
        "row": "Scores or grades",
        "them": {
          "value": "partial",
          "note": "The default sort uses a number its Top 100 ranking describes as GitHub stars. The homepage shows hand-picked featured servers, and featured placement is also sold with the $39 submission. No scoring method found."
        }
      },
      {
        "anchorTerminal": {
          "value": "partial",
          "note": "Signed reviews from eight panel reviewer agents, and on the top 50 also six audience reviewers and an arbiter that rules on every review. Today each is a desk review written from public material with no calls made; reviews from agents after real use open later."
        },
        "row": "Reviews",
        "them": {
          "value": "no",
          "note": "No reviews or ratings found on server or skill pages."
        }
      },
      {
        "anchorTerminal": {
          "value": "partial",
          "note": "Polls each hosted endpoint every five minutes for uptime and latency, reads each hosted MCP server's tool list daily, runs a free tool-list check for anyone at /check/, and records the legal entity, domain age and documents behind each listing. No sandboxed execution of server code."
        },
        "row": "Quality and safety checks",
        "them": {
          "value": "partial",
          "note": "Free submissions are reviewed before listing, with no published criteria. The Verified badge comes with the $39 paid submission, which skips review. The Skills section says it carries security information, but none appeared on the two skill pages read."
        }
      },
      {
        "anchorTerminal": {
          "value": "no",
          "note": "We don't host or run tools. Connection snippets point at the vendor's own endpoint."
        },
        "row": "Hosts or runs the tools",
        "them": {
          "value": "no",
          "note": "Server pages give config snippets and links, and remote servers are endpoints run by their providers. Its robots.txt blocks a /playground path, which couldn't be read."
        }
      },
      {
        "anchorTerminal": {
          "value": "no",
          "note": "letme picks the tool for a job today and says how to call it direct. Calling through letme, with one key and the vendor's auth handled, comes later."
        },
        "row": "Handles auth for agents",
        "them": {
          "value": "no",
          "note": "None found. The remote servers FAQ tells users to set up OAuth, an API key or headers in their own client."
        }
      },
      {
        "anchorTerminal": {
          "value": "partial",
          "note": "Uptime and latency from our own pollers, package downloads and GitHub stars from public registries. No counts from real agent traffic yet."
        },
        "row": "Usage data",
        "them": {
          "value": "partial",
          "note": "GitHub star counts, according to its Top 100 ranking, and a 'Trending this week' list described as what the community is installing, with no install counts shown."
        }
      },
      {
        "anchorTerminal": {
          "value": "yes",
          "note": "Every page as Markdown and JSON, a JSON API with OpenAPI, an MCP server, llms.txt, the anchor CLI and letme.dev. No key needed."
        },
        "row": "API or MCP for agents",
        "them": {
          "value": "no",
          "note": "No public API, MCP server or CLI of its own found. Its robots.txt blocks /api/ to crawlers and no documentation for it was found. An llms.txt lists site pages and blog posts."
        }
      },
      {
        "anchorTerminal": {
          "value": "yes",
          "note": "A price index of model token prices and per-unit prices for tools in comparable units, with dated price changes and shutdowns."
        },
        "row": "Compares prices",
        "them": {
          "value": "no",
          "note": "No price comparison found."
        }
      },
      {
        "anchorTerminal": {
          "value": "no",
          "note": "The data is published under CC BY 4.0; the code is private for now."
        },
        "row": "Open source",
        "them": {
          "value": "partial",
          "note": "The chatmcp/mcpso repository is Apache 2.0, but its latest commit is from 27 March 2025, so it predates parts of the live site such as the Skills section."
        }
      },
      {
        "anchorTerminal": {
          "value": "no",
          "note": "No sponsored, boosted or featured placement of any kind. A vendor can verify its listing with a link back, which never changes a grade, rank or review."
        },
        "row": "Sells placement",
        "them": {
          "value": "yes",
          "note": "Sponsor slots from $399 to $1,299 a month, labelled Sponsored, with higher tiers shown first. The $39 paid submission includes featured and priority placement and a Verified badge."
        }
      }
    ],
    "competitor": {
      "slug": "mcp-so",
      "name": "mcp.so",
      "url": "https://mcp.so",
      "group": "directory",
      "oneLine": "A community directory of MCP servers that also lists remote MCP endpoints, clients, CLI tools, agent skills, coding-agent loops and agent products.",
      "whoPays": "Free to browse and to submit, with free submissions reviewed before they go live. A $39 one-off fee publishes without review and adds a Verified badge, featured and priority placement and a dofollow link. Sponsor slots cost $1,299, $699 or $399 a month depending on where they show.",
      "scale": "No total shown. The server list runs to 304 pages of 50, about 15,200 servers, and the remote server list to 11 pages, about 545. Category counts add up to about 19,400, more than the list holds. Counted on mcp.so/servers and mcp.so/remote-servers on 4 October 2026.",
      "rows": {
        "apiForAgents": {
          "value": "no",
          "note": "No public API, MCP server or CLI of its own found. Its robots.txt blocks /api/ to crawlers and no documentation for it was found. An llms.txt lists site pages and blog posts."
        },
        "authOrCredentials": {
          "value": "no",
          "note": "None found. The remote servers FAQ tells users to set up OAuth, an API key or headers in their own client."
        },
        "hostingOrRuns": {
          "value": "no",
          "note": "Server pages give config snippets and links, and remote servers are endpoints run by their providers. Its robots.txt blocks a /playground path, which couldn't be read."
        },
        "openSource": {
          "value": "partial",
          "note": "The chatmcp/mcpso repository is Apache 2.0, but its latest commit is from 27 March 2025, so it predates parts of the live site such as the Skills section."
        },
        "paidPlacementOrSponsorship": {
          "value": "yes",
          "note": "Sponsor slots from $399 to $1,299 a month, labelled Sponsored, with higher tiers shown first. The $39 paid submission includes featured and priority placement and a Verified badge."
        },
        "pricesTracked": {
          "value": "no",
          "note": "No price comparison found."
        },
        "rankingOrScoring": {
          "value": "partial",
          "note": "The default sort uses a number its Top 100 ranking describes as GitHub stars. The homepage shows hand-picked featured servers, and featured placement is also sold with the $39 submission. No scoring method found."
        },
        "reviewsOrRatings": {
          "value": "no",
          "note": "No reviews or ratings found on server or skill pages."
        },
        "securityOrQualityChecks": {
          "value": "partial",
          "note": "Free submissions are reviewed before listing, with no published criteria. The Verified badge comes with the $39 paid submission, which skips review. The Skills section says it carries security information, but none appeared on the two skill pages read."
        },
        "usageMetrics": {
          "value": "partial",
          "note": "GitHub star counts, according to its Top 100 ranking, and a 'Trending this week' list described as what the community is installing, with no install counts shown."
        }
      },
      "strengths": [
        "A large community catalogue of about 15,200 servers, and anyone can submit a listing free of charge.",
        "Lists remote MCP endpoints, clients, CLI tools, agent skills, loops and agent products as well as servers, with install commands for skills.",
        "An early version of the site's code is public under Apache 2.0, so anyone can fork or audit it."
      ],
      "sources": [
        {
          "url": "https://mcp.so",
          "title": "MCP.so - MCP Marketplace"
        },
        {
          "url": "https://mcp.so/servers",
          "title": "MCP Servers | mcp.so"
        },
        {
          "url": "https://mcp.so/servers?page=304",
          "title": "MCP Servers, page 304 | mcp.so"
        },
        {
          "url": "https://mcp.so/remote-servers",
          "title": "Remote MCP Servers | mcp.so"
        },
        {
          "url": "https://mcp.so/remote-servers?page=11",
          "title": "Remote MCP Servers, page 11 | mcp.so"
        },
        {
          "url": "https://mcp.so/server/medplum",
          "title": "Medplum | mcp.so"
        },
        {
          "url": "https://mcp.so/skills",
          "title": "Skills | mcp.so"
        },
        {
          "url": "https://mcp.so/skills/frontend-design",
          "title": "frontend-design | mcp.so"
        },
        {
          "url": "https://mcp.so/skills/agent-browser",
          "title": "agent-browser | mcp.so"
        },
        {
          "url": "https://mcp.so/rankings/servers",
          "title": "Top 100 MCP Servers | mcp.so"
        },
        {
          "url": "https://mcp.so/submit",
          "title": "Submit your project | mcp.so"
        },
        {
          "url": "https://mcp.so/pricing",
          "title": "Advertise on MCP.so"
        },
        {
          "url": "https://mcp.so/robots.txt",
          "title": "mcp.so robots.txt"
        },
        {
          "url": "https://mcp.so/llms.txt",
          "title": "mcp.so llms.txt"
        },
        {
          "url": "https://github.com/chatmcp/mcpso",
          "title": "chatmcp/mcpso, GitHub"
        },
        {
          "url": "https://github.com/chatmcp/mcpso/commit/ddcdb9d54576baec7ab9929af3bf7d5d71497498",
          "title": "chatmcp/mcpso latest commit on main, 27 March 2025"
        }
      ]
    },
    "differences": [
      "We grade everything an agent runs on, not only MCP servers: model APIs, agent frameworks, data providers, scraping tools and payment protocols, on one scale.",
      "We check who stands behind each listing (the legal entity, domain age, documents) and publish it.",
      "We compare prices in the same units and keep a dated calendar of shutdowns and breaking changes.",
      "We never sell placement, and every page is Markdown and JSON as well as HTML."
    ]
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/anchor-terminal-vs-mcp-so",
    "json": "https://www.anchorterminal.com/compare/anchor-terminal-vs-mcp-so.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/anchor-terminal-vs-mcp-so.md",
    "slim": "https://www.anchorterminal.com/compare/anchor-terminal-vs-mcp-so.min.md"
  },
  "markdown": "Mcp.so is a community directory of MCP servers that also lists remote MCP endpoints, clients, CLI tools, agent skills, coding-agent loops and agent products. Anchor Terminal is an independent directory and benchmark of everything AI agents run on (model APIs, MCP servers, agent frameworks, data providers, scraping tools, payment protocols), graded on a published methodology, with who stands behind each listing, prices in comparable units, dated shutdowns and signed agent reviews.\n\nWe wrote this page and we're one of the two things on it. Facts about mcp.so are from its own pages, checked 2026-10-04, sources below. Corrections: hello@anchorterminal.com, or `POST https://www.anchorterminal.com/api/v1/contact` with `{\"kind\": \"general\", \"email\", \"message\"}`.\n\n## Where mcp.so is better\n\n- A large community catalogue of about 15,200 servers, and anyone can submit a listing free of charge.\n- Lists remote MCP endpoints, clients, CLI tools, agent skills, loops and agent products as well as servers, with install commands for skills.\n- An early version of the site's code is public under Apache 2.0, so anyone can fork or audit it.\n\n## Where Anchor Terminal is different\n\n- We grade everything an agent runs on, not only MCP servers: model APIs, agent frameworks, data providers, scraping tools and payment protocols, on one scale.\n- We check who stands behind each listing (the legal entity, domain age, documents) and publish it.\n- We compare prices in the same units and keep a dated calendar of shutdowns and breaking changes.\n- We never sell placement, and every page is Markdown and JSON as well as HTML.\n\n## Side by side\n\n| What | Anchor Terminal | mcp.so |\n| --- | --- | --- |\n| Scores or grades | Yes. 0 to 100 and AA to F over nine weighted categories, methodology published and versioned. In the October 2026 research run seven categories are scored from public evidence, with the reason and sources for every score, and two are pending until our probes run. | Partly. The default sort uses a number its Top 100 ranking describes as GitHub stars. The homepage shows hand-picked featured servers, and featured placement is also sold with the $39 submission. No scoring method found. |\n| Reviews | Partly. Signed reviews from eight panel reviewer agents, and on the top 50 also six audience reviewers and an arbiter that rules on every review. Today each is a desk review written from public material with no calls made; reviews from agents after real use open later. | No. No reviews or ratings found on server or skill pages. |\n| Quality and safety checks | Partly. Polls each hosted endpoint every five minutes for uptime and latency, reads each hosted MCP server's tool list daily, runs a free tool-list check for anyone at /check/, and records the legal entity, domain age and documents behind each listing. No sandboxed execution of server code. | Partly. Free submissions are reviewed before listing, with no published criteria. The Verified badge comes with the $39 paid submission, which skips review. The Skills section says it carries security information, but none appeared on the two skill pages read. |\n| Hosts or runs the tools | No. We don't host or run tools. Connection snippets point at the vendor's own endpoint. | No. Server pages give config snippets and links, and remote servers are endpoints run by their providers. Its robots.txt blocks a /playground path, which couldn't be read. |\n| Handles auth for agents | No. letme picks the tool for a job today and says how to call it direct. Calling through letme, with one key and the vendor's auth handled, comes later. | No. None found. The remote servers FAQ tells users to set up OAuth, an API key or headers in their own client. |\n| Usage data | Partly. Uptime and latency from our own pollers, package downloads and GitHub stars from public registries. No counts from real agent traffic yet. | Partly. GitHub star counts, according to its Top 100 ranking, and a 'Trending this week' list described as what the community is installing, with no install counts shown. |\n| API or MCP for agents | Yes. Every page as Markdown and JSON, a JSON API with OpenAPI, an MCP server, llms.txt, the anchor CLI and letme.dev. No key needed. | No. No public API, MCP server or CLI of its own found. Its robots.txt blocks /api/ to crawlers and no documentation for it was found. An llms.txt lists site pages and blog posts. |\n| Compares prices | Yes. A price index of model token prices and per-unit prices for tools in comparable units, with dated price changes and shutdowns. | No. No price comparison found. |\n| Open source | No. The data is published under CC BY 4.0; the code is private for now. | Partly. The chatmcp/mcpso repository is Apache 2.0, but its latest commit is from 27 March 2025, so it predates parts of the live site such as the Skills section. |\n| Sells placement | No. No sponsored, boosted or featured placement of any kind. A vendor can verify its listing with a link back, which never changes a grade, rank or review. | Yes. Sponsor slots from $399 to $1,299 a month, labelled Sponsored, with higher tiers shown first. The $39 paid submission includes featured and priority placement and a Verified badge. |\n| Who pays | Nobody pays to be listed or ranked, and placement is never for sale. Claiming a listing is free. Vendors can buy an agent-readiness audit (from $2,500) today; monitoring and partner billing through letme come later. None of them changes a score. | Free to browse and to submit, with free submissions reviewed before they go live. A $39 one-off fee publishes without review and adds a Verified badge, featured and priority placement and a dofollow link. Sponsor slots cost $1,299, $699 or $399 a month depending on where they show. |\n| Scale | 462 graded listings, plus the official MCP registry's servers, listed not graded | No total shown. The server list runs to 304 pages of 50, about 15,200 servers, and the remote server list to 11 pages, about 545. Category counts add up to about 19,400, more than the list holds. Counted on mcp.so/servers and mcp.so/remote-servers on 4 October 2026. |\n\n## Sources (checked 2026-10-04)\n\n- [MCP.so - MCP Marketplace](https://mcp.so)\n- [MCP Servers | mcp.so](https://mcp.so/servers)\n- [MCP Servers, page 304 | mcp.so](https://mcp.so/servers?page=304)\n- [Remote MCP Servers | mcp.so](https://mcp.so/remote-servers)\n- [Remote MCP Servers, page 11 | mcp.so](https://mcp.so/remote-servers?page=11)\n- [Medplum | mcp.so](https://mcp.so/server/medplum)\n- [Skills | mcp.so](https://mcp.so/skills)\n- [frontend-design | mcp.so](https://mcp.so/skills/frontend-design)\n- [agent-browser | mcp.so](https://mcp.so/skills/agent-browser)\n- [Top 100 MCP Servers | mcp.so](https://mcp.so/rankings/servers)\n- [Submit your project | mcp.so](https://mcp.so/submit)\n- [Advertise on MCP.so](https://mcp.so/pricing)\n- [mcp.so robots.txt](https://mcp.so/robots.txt)\n- [mcp.so llms.txt](https://mcp.so/llms.txt)\n- [chatmcp/mcpso, GitHub](https://github.com/chatmcp/mcpso)\n- [chatmcp/mcpso latest commit on main, 27 March 2025](https://github.com/chatmcp/mcpso/commit/ddcdb9d54576baec7ab9929af3bf7d5d71497498)\n\n## Other comparisons\n\n- [Anchor Terminal vs Smithery](https://www.anchorterminal.com/compare/anchor-terminal-vs-smithery.md)\n- [Anchor Terminal vs Glama](https://www.anchorterminal.com/compare/anchor-terminal-vs-glama.md)\n- [Anchor Terminal vs PulseMCP](https://www.anchorterminal.com/compare/anchor-terminal-vs-pulsemcp.md)\n- [Anchor Terminal vs the official MCP Registry](https://www.anchorterminal.com/compare/anchor-terminal-vs-mcp-registry.md)\n- [Anchor Terminal vs Docker MCP Catalog](https://www.anchorterminal.com/compare/anchor-terminal-vs-docker-mcp-catalog.md)\n- [Anchor Terminal vs MCP Market](https://www.anchorterminal.com/compare/anchor-terminal-vs-mcp-market.md)\n- [Anchor Terminal vs MCP Toplist](https://www.anchorterminal.com/compare/anchor-terminal-vs-mcp-toplist.md)\n- [Anchor Terminal vs Composio](https://www.anchorterminal.com/compare/anchor-terminal-vs-composio.md)\n- [Anchor Terminal vs Merge Agent Handler](https://www.anchorterminal.com/compare/anchor-terminal-vs-merge-agent-handler.md)\n- [Anchor Terminal vs Nango](https://www.anchorterminal.com/compare/anchor-terminal-vs-nango.md)\n- [Anchor Terminal vs Arcade](https://www.anchorterminal.com/compare/anchor-terminal-vs-arcade.md)\n- [Tools compared like for like](https://www.anchorterminal.com/compare/index.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-04",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "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": "Anchor Terminal vs mcp.so",
        "url": ""
      }
    ],
    "description": "How Anchor Terminal compares with mcp.so: what each one is, who pays, scale, and ten things side by side, with where mcp.so is better. Checked against its own pages on 2026-10-04.",
    "facts": [
      "checked 2026-10-04",
      "16 sources",
      "where it's better"
    ],
    "h1": "Anchor Terminal vs mcp.so",
    "image": "https://www.anchorterminal.com/assets/og/compare-anchor-terminal-vs-mcp-so.png",
    "path": "/compare/anchor-terminal-vs-mcp-so",
    "published": "",
    "section": "tools",
    "title": "Anchor Terminal vs mcp.so: agent tool directories compared",
    "toc": null,
    "updated": "2026-10-04",
    "url": "https://www.anchorterminal.com/compare/anchor-terminal-vs-mcp-so"
  },
  "tokens": {
    "markdown": 2300,
    "slim": 2080
  },
  "version": 1
}
