# Realworldapis MCP server

Source: https://glimind.com/server/mcp-registry%2Fcom.realworldapis%2Frealworldapis
Registry id: `mcp-registry/com.realworldapis/realworldapis`
Status: live (checked 2026-10-27T17:02:30.815Z)

## Verdict

Realworldapis MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 273 ms median handshake and 0 outages in 90 days. Its agent-readiness grade is A (99/100) across 6 tools, costing an agent about 3,453 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 42% of MCP servers |
| Median handshake latency | 273 ms | 64% of MCP servers |
| p95 handshake latency | 2122 ms | — |
| Checks in 30 days | 4,995 | — |
| Outages, 90 days | 0 | — |
| Median recovery | — | — |
| Agent-readiness score | 99/100 (A) | 92% of MCP servers |
| Tools | 6 | — |
| Tool-list size for an agent | ~3,453 tokens | 43% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "realworldapis-mcp-server": {
      "type": "http",
      "url": "https://realworldapis-api.realworldapis.workers.dev/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http realworldapis-mcp-server https://realworldapis-api.realworldapis.workers.dev/mcp
```

## Tools (6)

- `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 cons
- `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 k
- `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 executi
- `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 
- `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 exec
- `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

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.