81trust / 100

Discover

by mcp-discovery in Onchain & crypto

x402 APIPassing, checked 3 h ago

Find MCP servers matching a need, ranked by semantic similarity over a curated snapshot of MCP servers. Returns name, endpoint, description, source registry and a 0-1 relevance per match. Paid POST: up to 25 matches. Try GET /discover/sample.

POST https://x402.agentindex.world/discover

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
74 ms typical, 74 ms slowest 5%
Last check
3 h ago
Next check
any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://x402.agentindex.world/discover" \
  -H "content-type: application/json" \
  -d '{"q":"read a PDF and give me markdown"}'
import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { ExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client().register(
  "eip155:8453",
  new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? Preflight it first for $0.005:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fx402.agentindex.world%2Fdiscover
const res = await pay("https://x402.agentindex.world/discover", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"q":"read a PDF and give me markdown"}),
});
console.log(await res.json());

Example input

{
  "q": "read a PDF and give me markdown"
}

Example output

{
  "matches": 3,
  "min_similarity": 0.3,
  "q": "read a PDF and give me markdown",
  "results": [
    {
      "description": "Extract a public PDF into clean markdown text, plus metadata and a real token count.",
      "name": "PDF Extract MCP",
      "observed_at": "2026-09-02T19:07:49.374328Z",
      "registry": "registre-mcp",
      "relevance": 0.7211,
      "url": "https://example.org/mcp/"
    },
    {
      "description": "Document conversion to markdown and structured text for LLM agents.",
      "name": "Docling Server",
      "observed_at": "2026-09-10T12:00:00Z",
      "registry": "annuaire",
      "relevance": 0.6487,
      "url": null
    },
    {
      "description": "Deep code indexing for AI agents. FTS5 + embeddings + call graphs. Fully local.",
      "name": "Srclight",
      "observed_at": "2026-09-15T08:30:00Z",
      "registry": "registre-mcp",
      "relevance": 0.4102,
      "url": "https://example.com/mcp/"
    }
  ],
  "snapshot_date": "2026-09-18",
  "snapshot_rows": 10327
}

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
3 h agoPassed402218 ms$0.001
8 h agoPassed40274 ms$0.001