nohumans.directory — MCP Server

Find and vet paid x402 API services before an agent spends money on them.

A discovery and trust layer for paid x402 services. Every listing is re-probed every 5 minutes, and each carries a recency-weighted reliability score built from that probe history — so an agent can check whether an endpoint actually responds before paying for it.

Free. No API key. No signup. No account.

Live stats: https://nohumans.directory · REST API: https://api.nohumans.directory

Why this exists

Most x402 directories are catalogs: they list what exists. None of them tell you whether a listing still works.

This one probes every endpoint it lists, every 5 minutes, and keeps the history. A listing moves unverified → verified only after sustained clean probes, and falls to failing when it stops responding. The reliability score is recency-weighted, so a service that broke yesterday can't hide behind a good month.

Every listing also carries a hand-written description of what the service actually does — which sounds mundane until you try semantic search against a catalog of bare URLs.

Related MCP server: x402search

Installation

Remote server, streamable HTTP. No install, no build step, no credentials.

Claude Code

claude mcp add --transport http nohumans https://api.nohumans.directory/mcp

Claude Desktop / any stdio-only client

{
  "mcpServers": {
    "nohumans": {
      "command": "npx",
      "args": ["mcp-remote", "https://api.nohumans.directory/mcp"]
    }
  }
}

Direct remote connection

https://api.nohumans.directory/mcp

Transport: streamable-http · Authentication: none · Cost: free

Agent Skill

For agents that support the Agent Skills standard (Claude Code, Codex, and others), install the skill so the agent knows how to use the tools below intelligently — when to prefer verified listings, how to read score/status/x402_version/on-chain payment evidence, and how to report a real outcome via tx_hash:

mkdir -p ~/.claude/skills/nohumans-directory
curl -o ~/.claude/skills/nohumans-directory/SKILL.md \
  https://raw.githubusercontent.com/jalcodev/nohumans-mcp/main/skills/nohumans-directory/SKILL.md

Tools

find_paid_service

Search paid x402 services by capability, price ceiling, and minimum reliability score. Returns ranked results — verified services first, then by reliability, then by price.

get_service_details

Full record for a single service: pricing, accepted chains, request and response schemas, current status, reliability score, median latency, probe count, protocol version (x402_version), and 30-day on-chain payment volume — everything an agent needs before making a paid call.

Example

An agent that needs FX rates and won't pay more than half a cent, and refuses to touch anything with a reliability score under 0.9:

find_paid_service(query="fx rates", max_price=0.005, min_score=0.9)

Returns matching services with their live reliability scores and median latency, so the agent can pick one and pay with confidence.

REST API

The same data is available over plain HTTP, no MCP client required:

# Search
curl 'https://api.nohumans.directory/v1/discover?q=fx&max_price=0.005&min_score=0.9'

# Full detail for one listing
curl 'https://api.nohumans.directory/v1/listings/{id}'

# Full transition history for one listing
curl 'https://api.nohumans.directory/v1/listings/{id}/history'

# Live directory stats
curl 'https://api.nohumans.directory/v1/stats'

# What agents search for and can't find
curl 'https://api.nohumans.directory/v1/demand'

Agent-readable docs: /llms.txt

Listing a service

Self-serve, no account:

curl -X POST https://api.nohumans.directory/v1/listings \
  -H 'content-type: application/json' -d '{
    "name": "Your service",
    "description": "What it does, in a sentence an agent can act on.",
    "endpoint_url": "https://api.example.com/v1/thing",
    "category": "data.example",
    "price_amount": 0.001,
    "price_currency": "USDC",
    "chains": ["base"]
  }'

Submissions land as unverified and are prioritized in the probe queue — typically checked within about 5 minutes. Sustained clean probes promote a listing to verified; sustained failures demote it. Ranking is earned by uptime, never sold.

Save the claim_token from the response — it's your edit key, shown once.

Full submission guide, including the HTTP 402 requirement that causes most rejected listings: SUBMITTING.md

How verification works

• Every listing is probed on a 5-minute cycle from independent infrastructure, prioritized by need — new and recovering listings are checked closer to every cycle; long-stable verified listings are checked somewhat less often.

• A live x402 endpoint answers an unpaid request with HTTP 402 and payment requirements — that alone proves liveness and protocol conformance. Probes never send payment.

• Reliability scores are recency-weighted: recent behaviour dominates.

• Status lifecycle: unverified → verified → failing → delisted.

• If a listing's declared payment address changes, its reputation resets and status drops back to unverified — an old score never carries over to a new, unproven payment destination.

• 30-day on-chain payment volume (distinct payers, transaction count) is checked daily from public chain data — separate evidence from the probe score, never blended into it. It shows real payment activity; it doesn't verify output quality.

• Probes originate from our infrastructure, not from sellers. Reliability cannot be self-reported.

License

MIT for this documentation. The directory service itself is free to use.

Contact

hello@nohumans.directory