intermcp
An MCP server that lets separate Claude Code agents send messages to each other. It supports running several independent agents in parallel on the same project.
Share on XLicense: MIT
Overview
intermcp is an MCP server that lets separate Claude Code agents message each other. Claude Code subagents share a session and run one after another, so parallel work needs separate sessions, which normally cannot see each other and may duplicate or conflict. Each session runs an intermcp serve process connected to a shared local daemon that routes messages, using Claude Code channels to push them into sessions.
Key features
- Agents discover other running agents
- Real-time messages between separate Claude Code sessions
- Local daemon on localhost routes messages
- Uses Claude Code channels to deliver messages
Best for
Developers running several independent Claude Code sessions on one codebase, for example one building a feature and another writing tests, who want them to coordinate.
- Upstream
- leonardcser/intermcp
- Fork on GitHub
- Guo-astro/intermcp
- Upstream stars
- 0
- Category
- AI agents and LLM tools
- Language
- Go
- License
- MIT
- Forked
- 2026-03-23
- Sync status
- In syncLast synced 2026-09-29
More in AI agents and LLM tools
A free desktop app where children in non-English-speaking countries practice English speaking and listening by talking with an AI companion. It can run locally and offline.
Forked 2026-09-28Last synced 2026-09-29License: MITAI agents and LLM toolsGitHub
An agent skill for Chinese patents. It helps find patentable points, write disclosure documents, explain patents in plain language, follow policy changes and assist with examination replies.
Forked 2026-09-28Last synced 2026-09-29License: MITAI agents and LLM toolsGitHub
A minimal Python library from Hugging Face for building AI agents that write and run code to solve tasks. It lets you set up capable agents in a few lines.
Forked 2026-09-28Last synced 2026-09-29License: Apache-2.0AI agents and LLM toolsGitHub
An open-source benchmark that measures how well AI agents handle realistic legal work. It provides tasks and evaluation for improving legal agents.
Forked 2026-09-28Last synced 2026-09-29License: MITAI agents and LLM toolsGitHub