Skip to main content
Glama
AgentAnycast MCP Server

AgentAnycast MCP Server

Official
by AgentAnycast

AgentAnycast MCP Server

Turn any AI tool into a peer-to-peer agent hub. Discover, communicate with, and orchestrate AI agents across any network -- encrypted, decentralized, zero config.

PyPI License

uvx agentanycast-mcp

Works with Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, JetBrains, Gemini CLI, Amazon Q, Cline, Continue, Zed, Roo Code, and ChatGPT.

Setup

Pick your platform and add the config below. That's the entire setup -- the daemon downloads and starts automatically on first run.

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "agentanycast": {
      "command": "uvx",
      "args": ["agentanycast-mcp"]
    }
  }
}
claude mcp add agentanycast -- uvx agentanycast-mcp

Add to .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "agentanycast": {
      "command": "uvx",
      "args": ["agentanycast-mcp"]
    }
  }
}

Add to .vscode/mcp.json:

{
  "servers": {
    "agentanycast": {
      "command": "uvx",
      "args": ["agentanycast-mcp"]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "agentanycast": {
      "command": "uvx",
      "args": ["agentanycast-mcp"]
    }
  }
}

Settings -> Tools -> AI -> MCP Servers -> Add:

{
  "servers": {
    "agentanycast": {
      "command": "uvx",
      "args": ["agentanycast-mcp"]
    }
  }
}

Add to ~/.gemini/settings.json:

{
  "mcpServers": {
    "agentanycast": {
      "command": "uvx",
      "args": ["agentanycast-mcp"]
    }
  }
}

Add to ~/.aws/amazonq/mcp.json:

{
  "mcpServers": {
    "agentanycast": {
      "command": "uvx",
      "args": ["agentanycast-mcp"]
    }
  }
}

Add to Cline MCP settings (VS Code: Ctrl+Shift+P -> "Cline: MCP Servers"):

{
  "mcpServers": {
    "agentanycast": {
      "command": "uvx",
      "args": ["agentanycast-mcp"]
    }
  }
}

Add to ~/.continue/config.json:

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "stdio",
          "command": "uvx",
          "args": ["agentanycast-mcp"]
        }
      }
    ]
  }
}

Add to Zed settings (~/.config/zed/settings.json):

{
  "context_servers": {
    "agentanycast": {
      "command": {
        "path": "uvx",
        "args": ["agentanycast-mcp"]
      }
    }
  }
}

Add to Roo Code MCP settings (VS Code: Ctrl+Shift+P -> "Roo Code: MCP Servers"):

{
  "mcpServers": {
    "agentanycast": {
      "command": "uvx",
      "args": ["agentanycast-mcp"]
    }
  }
}

Deploy the server with HTTP transport:

agentanycast-mcp --transport http --port 8080
# or: docker run -p 8080:8080 agentanycast/mcp-server

Then add http://your-server:8080/mcp in ChatGPT developer settings.

Related MCP server: slm-mesh

What You Can Do

Once connected, ask your AI assistant:

  • "Find agents that can translate Japanese" -- discovers agents on the P2P network

  • "Send 'summarize this article' to the translate agent" -- encrypted task delivery

  • "What agents are connected right now?" -- lists connected peers

  • "What's my Peer ID?" -- shows your node's identity and DID

Available Tools

Tool

Description

Example prompt

discover_agents

Find agents by skill

"Find agents that can translate"

send_task

Send an encrypted task to an agent

"Send 'hello' to peer 12D3KooW..."

get_task_status

Check the result of a sent task

"What was the result of that task?"

get_agent_card

Get an agent's capabilities

"What can that agent do?"

list_connected_peers

List all connected P2P peers

"Who's online?"

get_node_info

Get this node's Peer ID, DID, status

"What's my agent info?"

Configuration

Environment Variables

Set these in the "env" section of your MCP config:

Variable

Description

Default

AGENTANYCAST_RELAY

Relay server multiaddr for cross-network P2P

None (LAN only)

AGENTANYCAST_HOME

Data directory for daemon state

~/.agentanycast

Example with relay for cross-network communication:

{
  "mcpServers": {
    "agentanycast": {
      "command": "uvx",
      "args": ["agentanycast-mcp"],
      "env": {
        "AGENTANYCAST_RELAY": "/ip4/relay.agentanycast.io/tcp/4001/p2p/12D3KooW..."
      }
    }
  }
}

CLI Arguments

agentanycast-mcp [--transport stdio|http] [--port 8080] [--relay MULTIADDR] [--home DIR]

CLI arguments take priority over environment variables.

How It Works

Your AI Tool (Claude, Cursor, VS Code, ...)
    |
    | MCP protocol (stdio or HTTP)
    v
AgentAnycast MCP Server
    |
    | gRPC (Unix domain socket)
    v
AgentAnycast Daemon (Go)
    |
    | libp2p (TCP/QUIC + Noise_XX encryption + NAT traversal)
    v
Remote AI Agents (anywhere in the world)
  • Zero config -- uvx agentanycast-mcp handles everything. The daemon is auto-downloaded and managed.

  • Zero API keys -- agents are identified by cryptographic Peer IDs (Ed25519), not accounts or tokens.

  • End-to-end encrypted -- Noise_XX protocol. Even relay servers see only ciphertext.

  • NAT traversal -- works behind firewalls with automatic hole-punching and relay fallback.

What Makes This Different

This is the only MCP server that connects to a decentralized peer-to-peer network of AI agents. Other MCP servers connect to specific SaaS APIs. AgentAnycast connects you to any AI agent, anywhere, with no intermediary that can read your messages.

Troubleshooting

Daemon fails to start

  • Check that port 4001 (TCP) is not in use: lsof -i :4001

  • Try a clean state: rm -rf ~/.agentanycast && uvx agentanycast-mcp

No agents found on discover

  • Agents must be on the same LAN (mDNS) or connected to the same relay

  • Set AGENTANYCAST_RELAY to connect across networks

Connection timeout

  • Behind a strict firewall? Set a relay address. The relay provides fallback connectivity.

  • Check daemon logs: cat ~/.agentanycast/daemon.log

"uvx" not found

  • Install uv: curl -LsSf https://astral.sh/uv/install.sh | sh

  • Or install directly: pip install agentanycast-mcp

Tool calls failing

  • Restart your AI tool after adding the MCP config

  • Verify config JSON syntax (no trailing commas)

License

Apache License, Version 2.0

Available Tools

6 tools
discover_agentsA

Find AI agents on the P2P network that offer a specific skill.

Use this to search for agents before sending them tasks. For example, discover_agents("translate") finds agents that can translate text.

Args: skill: The skill to search for (e.g. "translate", "summarize", "code-review").

Inputs: skill (required). Returns: result

get_agent_cardA

Get the capability card (A2A Agent Card) for a peer or this node.

Returns the agent's name, description, skills, PeerID, and DID.

Args: peer_id: PeerID of the agent to query. Leave empty or "self" to get this node's card.

Inputs: peer_id. Returns: result

get_node_infoA

Get this node's PeerID, DID, and connection status on the P2P network.

Inputs: no named parameters. Returns: result

get_task_statusA

Get the current status and result of a previously sent task.

Args: task_id: The task ID returned by send_task.

Inputs: task_id (required). Returns: result

list_connected_peersA

List all peers currently connected to this node over the P2P network.

Inputs: no named parameters. Returns: result

send_taskA

Send an encrypted task to a remote AI agent and wait for the result.

The target determines how the agent is reached:

  • PeerID (starts with "12D3KooW"): direct encrypted P2P connection

  • Skill name (e.g. "translate"): automatic routing to the best agent

  • HTTP URL (starts with "http"): standard A2A HTTP bridge

Args: target: PeerID, skill name, or HTTP URL of the target agent. message: The message or instruction to send to the agent. timeout: Maximum seconds to wait for a response (default: 30).

Inputs: target (required), message (required), timeout. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: searching for agents, retrieving agent details, getting node info, checking task status, listing peers, and sending tasks. No overlapping functionality.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern in snake_case, such as 'discover_agents', 'get_agent_card', and 'send_task', making the API easy to predict.

    Tool Count5/5

    6 tools cover the core workflows of agent discovery, peer interaction, and task management without being excessive or insufficient for the server's scope.

    Completeness4/5

    The set covers discovery, sending tasks, status tracking, and node/peer info. Missing a tool to list or cancel tasks is a minor gap but does not severely hinder agent workflows.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers