AgentMCP: The Universal System for AI Agent Collaboration

Created By
grupa-aia year ago
MCPAgent for Grupa.AI Multi-agent Collaboration Network (MACNET) with Model Context Protocol (MCP) capabilities baked in
Overview

What is AgentMCP?

AgentMCP is a Multi-Agent Collaboration Platform (MCP) that enables seamless collaboration between AI agents using the Model Context Protocol (MCP). It allows developers to convert any agent into an MCP-compatible agent with a simple decorator.

How to use AgentMCP?

To use AgentMCP, install it via pip and decorate your agent class with @mcp_agent. This single line of code integrates your agent into the Multi-Agent Collaboration Network (MACNet).

Key features of AgentMCP?

  • One-line integration to convert agents into MCP agents.
  • Automatic network registration for agents.
  • Framework-agnostic, compatible with various AI frameworks.
  • Built-in adapters for popular frameworks like Langchain and CrewAI.

Use cases of AgentMCP?

  1. Collaborating on complex tasks with multiple specialized agents.
  2. Enabling agents to share context and knowledge across different frameworks.
  3. Creating a network of agents that can discover and utilize each other's capabilities.

FAQ from AgentMCP?

  • Can I use AgentMCP with any AI framework?

Yes! AgentMCP is designed to work with any AI framework or custom implementation.

  • How do agents communicate in the network?

Agents communicate through a centralized task management system using HTTP/FastAPI.

  • Is there a community for support?

Yes! Join our Discord community for discussions and support.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
grupa-ai
Star
6
Language
Python
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago