# agent-discovery-mcp

> agent-discovery-mcp — claynsn-agent-discovery-mcp. Use this tool when you need to enable your AI coding agent to discover and pay on-chain agents in a seamless and automated manner. The agent-discovery-mcp tool solves the problem of complex payment workflows by providing a straightforward HTTPS request interface, eliminating the need for smart accounts, bundlers, or relays. It is ideal for use cases where ERC-8004 registered agents need to be integrated with AI coding agents, such as Claude Code or Codex, using the x402 protocol.

Canonical page: https://skillsregistry.net/skills/claynsn-agent-discovery-mcp  
JSON: https://api.skillsregistry.net/v1/skills/claynsn-agent-discovery-mcp

## Description

An MCP server that lets your AI coding agent (Claude Code, OpenClaw, Codex, Cursor, etc.) discover and pay on-chain agents registered on ERC-8004, using Coinbase's official x402 protocol.

No smart account. No bundler. No relay. Just your EOA, an HTTPS request, and an automatic 402 → sign → retry flow.

## Trust

- **Trust score (0–1):** 0.95
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/x1irxovkk9)
- **Repository:** <https://github.com/ClayYTsai/agent-discovery-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "claynsn-agent-discovery-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/claynsn-agent-discovery-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/claynsn-agent-discovery-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt