Enterprise DNA Enterprise DNA
M MCP Servers Developer low

geondongkim/geond-agent-protocol

by Various

Local-first MCP server for shared memory, reservations, handoffs, and review evidence across AI coding agents.

MCP

geondongkim/geond-agent-protocol

Added 7 June 2026

#agent-coordination #agent-memory #ai-agents #ai-coding #claude-code #code-graph #codex #copilot

Overview

A local-first MCP server that provides shared memory, reservations, handoffs, and review evidence for AI coding agents. It enables multiple agents to coordinate and persist context without relying on external services.

Best for

Best for
Developers experimenting with multi-agent coding systems who want a lightweight, local coordination layer.

Use cases

  • Orchestrating multi-agent coding workflows with shared state
  • Handing off tasks between agents with reservation and review tracking
  • Persisting agent context and evidence for later inspection

How to use

Install

uv run geond-mcp

Tools exposed

  • uv
  • docker
  • git
  • ripgrep

Tested with

Copilot Chat, Codex, Claude Code, Antigravity, Manus, Continue

Notes

A local-first MCP server that provides shared memory, reservations, handoffs, and review evidence for AI coding agents. It enables multiple agents to coordinate and persist context without relying on external services.

1 stars on GitHub. Last updated 2026-06-07. Licensed Apache-2.0.

Use cases

  • Orchestrating multi-agent coding workflows with shared state
  • Handing off tasks between agents with reservation and review tracking
  • Persisting agent context and evidence for later inspection

Pros

  • Local-first design avoids external dependencies for coordination
  • Provides structured mechanisms for agent handoffs and reviews
  • Written in Python, easy to integrate into existing MCP toolchains

Cons

  • Very early stage with only 1 star and limited community adoption
  • Potential scalability or reliability issues due to a single maintainer
  • Requires agents to implement MCP client support to use

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Local-first design avoids external dependencies for coordination
  • Provides structured mechanisms for agent handoffs and reviews
  • Written in Python, easy to integrate into existing MCP toolchains

Cons

  • Very early stage with only 1 star and limited community adoption
  • Potential scalability or reliability issues due to a single maintainer
  • Requires agents to implement MCP client support to use
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

Running a business, not writing the code? See the MCP servers picked for operators, and get your first one wired up with us.

Operator picks