Skip to content
RealWorldAPIs logo

RealWorldAPIs MCP server

Which MCP servers are RealWorldAPIs's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-25

← Back to RealWorldAPIs

Whose server it is
  • Registry namecom.realworldapis/realworldapisverified in the MCP registry

The registry name sits under realworldapis.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-25
  • Stateanswerschecked 2026-10-25
  • Tools6
  • Server calls itselfrealworldapis
  • Server version3.4.1
  • Protocol version2025-06-18

On 2026-10-25 the server answered initialize and tools/list without a sign-in. First answer in 179 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: search and filter verified real-world APIs by category; match a task to APIs with checked access requirements; compare a shortlist of APIs by capability and readiness.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • For "search and filter verified real-world APIs by category", the likely first call is search_apis.
  • For "match a task to APIs with checked access requirements", the likely first call is find_api_for_task.
  • For "compare a shortlist of APIs by capability and readiness", the likely first call is compare_apis.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 2, the first on 2026-10-25
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer84 ms
  • Space in an agent's context≈ 3,249 tokensthe definitions of all its tools (6), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results6 of 6 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · search and filter verified real-world APIs by category
  • can do · match a task to APIs with checked access requirements
  • can do · compare a shortlist of APIs by capability and readiness

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers6 tools · read 2026-10-25
  • find_api_for_task

    Find the best APIs for a natural-language physical-world task. Use this for open-ended task or outcome-based recommendations; use search_apis when you already know exact filters, get_api for one known API, or compare_apis for known…

  • search_apis

    Search the canonical registry when you already know keywords or exact requirements. All supplied filter groups combine with AND logic; array capability filters require every supplied value, and protocol fields match the exact…

  • search_capabilities

    Search the canonical 770-capability Verified/High decision graph directly. Use this when the question is about what an agent can actually do and under what execution conditions: task/capability text, API, category, action type, acted-on…

  • verify_requirement

    Verify whether one specific API can satisfy one exact requirement using the canonical Verified/High capability graph plus linked assertion evidence. Returns YES, NO, PARTIAL or UNKNOWN with matched capability, access/setup prerequisites…

  • get_api

    Retrieve one canonical API decision profile when you already know its name or slug. The response includes the full Verified/High capability profile with execution, access, approval, reversibility, physical-consequence and evidence fields…

  • compare_apis

    Compare 2–8 already-known APIs side by side using canonical catalog fields plus capability-graph summary fields such as verified capability count, physical consequences, approval relevance and irreversibility. Use get_api for the full…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "realworldapis": {
      "type": "http",
      "url": "https://mcp.realworldapis.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http realworldapis https://mcp.realworldapis.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://mcp.realworldapis.com/mcp as a custom connector in the settings.

OpenAPI spec

8 paths, read 2026-10-25. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.