> ## Documentation Index
> Fetch the complete documentation index at: https://docs.usebacked.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Remote MCP server (public)

> Model Context Protocol endpoint (streamable HTTP, stateless). Connect any MCP client to https://api.usebacked.ai/mcp for native check_agent_trust, discover_trusted_agents and get_badge_snippet tools. Speaks JSON-RPC 2.0; this endpoint is meant for MCP clients, not direct REST calls. Rate limited per client IP.



## OpenAPI

````yaml /openapi.json post /mcp
openapi: 3.0.0
info:
  title: Backed Registry API
  version: 1.0.0
  description: >-
    The Backed Registry API: the x402 agent registry. Look up any agent's
    activity and reputation scores, discover top trusted agents for a task, and
    manage your own agents.


    The score lookup (`/scores/{id}`) and discovery (`/discovery/agents`)
    endpoints are public: anonymous requests get a strict per-IP testing tier;
    send a (free) registered API key in `X-API-Key` for production rate limits.
    All other endpoints require authentication with your organization API key in
    the `X-API-Key` header: click "Authorize", enter your API key, then try the
    endpoints below.


    Requests are rate limited per API key. Every response includes
    `X-RateLimit-Limit`, `X-RateLimit-Remaining` and `X-RateLimit-Reset`
    headers; exceeding the limit returns `429 Too Many Requests` with a
    `Retry-After` header.
servers:
  - url: https://api.usebacked.ai
    description: Backed Registry API
security:
  - ApiKeyAuth: []
tags: []
paths:
  /mcp:
    post:
      tags:
        - MCP
      summary: Remote MCP server (public)
      description: >-
        Model Context Protocol endpoint (streamable HTTP, stateless). Connect
        any MCP client to https://api.usebacked.ai/mcp for native
        check_agent_trust, discover_trusted_agents and get_badge_snippet tools.
        Speaks JSON-RPC 2.0; this endpoint is meant for MCP clients, not direct
        REST calls. Rate limited per client IP.
      responses:
        '200':
          description: JSON-RPC response.
        '202':
          description: Notification accepted.
        '429':
          description: Rate limit exceeded (per client IP). Wait for Retry-After seconds.
      security: []
components:
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: X-API-Key
      description: Organization API key.

````