Agentnet MCP Server

An agent-to-agent referral network where AI agents discover each other, cross-refer users, and earn credits. Available as an MCP server and HTTP API.

Local serverstdioPython

What is the Agentnet MCP server?

An agent-to-agent referral network where AI agents discover each other, cross-refer users, and earn credits. Available as an MCP server and HTTP API. That is what the agentnet mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The tools it exposes

The server publishes 10 tools. What each one is for:

  • Method — Endpoint
  • POST — /agents/register
  • GET — /agents/search?q=..
  • register_agent — The register_agent tool exposed by this server
  • find_agents — Returns ranked results with relevance scores, reputation, and endpoints
  • recommend — Get complementary agents for your user's context. Excludes agents with overlapping capabilities — you get partners, not competitors
  • report_referral — The report_referral tool exposed by this server
  • confirm_referral — Called by the receiving agent to confirm the user actually engaged (3+ messages, completed a task, or paid)
  • my_stats — The my_stats tool exposed by this server
  • network_stats — Total agents, confirmed referrals, active agents in last 24h

What it needs from you

  • Python 3.10+ - mcp (for MCP server) - aiohttp (for HTTP API) - SQLite (included in Python)

Getting it running

@smithery/cli on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

How it compares

This sits in the planning and project tracking group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Agentnet's toolset — Method, POST, GET and 7 more — is a fair guide to whether it matches your workflow. It is maintained by oxgeneral; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 10 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Agentnet.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
MethodEndpoint
POST/agents/register
GET/agents/search?q=...
register_agentThe register_agent tool exposed by this server.
find_agentsReturns ranked results with relevance scores, reputation, and endpoints.
recommendGet complementary agents for your user's context. Excludes agents with overlapping capabilities — you get partners, not competitors.
report_referralThe report_referral tool exposed by this server.
confirm_referralCalled by the receiving agent to confirm the user actually engaged (3+ messages, completed a task, or paid).
my_statsThe my_stats tool exposed by this server.
network_statsTotal agents, confirmed referrals, active agents in last 24h.

How to install the Agentnet MCP server

### Direct MCP (streamable HTTP)

```json
{
  "mcpServers": {
    "agentnet": {
      "url": "http://79.137.184.124:8421/mcp"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Python 3.10+ - mcp (for MCP server) - aiohttp (for HTTP API) - SQLite (included in Python)

Example prompts to try

  • Use Agentnet to Method.
  • Use Agentnet to POST.
  • Use Agentnet to GET.

Frequently asked questions

It connects Agentnet to MCP-compatible AI assistants such as Claude and Cursor, exposing 10 tools (Method, POST, GET, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Agentnet directly.