concord-mcp

Name: concord-mcp
Author: Get-Concord-AI

Pending

Shared work-state for coding agents: claim work, leave handoffs, and generate review packets before PRs, over MCP.

79stars

4forks

TypeScript

Installation

# Add to your Claude Code skills
git clone https://github.com/Get-Concord-AI/concord-mcp

Getting Started

Guides for using ai agents skills like concord-mcp.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

README.md

Frequently Asked Questions

What is concord-mcp?

concord-mcp is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by Get-Concord-AI. Shared work-state for coding agents: claim work, leave handoffs, and generate review packets before PRs, over MCP. It has 79 GitHub stars.

Is concord-mcp safe to use?

concord-mcp's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.

How do I install concord-mcp?

Clone the repository with "git clone https://github.com/Get-Concord-AI/concord-mcp" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is concord-mcp written in?

concord-mcp is primarily written in TypeScript. It is open-source under Get-Concord-AI on GitHub, so you can review or fork the full source.

Are there alternatives to concord-mcp?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh concord-mcp against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

superpowers

by obra

An agentic skills framework & software development methodology that works.

234,966

ai-agent-skills claude-tester

Concord MCP

Shared work-state for coding agents. Concord MCP gives Claude Code, Codex, Cursor, and other MCP-capable coding assistants a shared work log. Agents can claim work, share task context, leave handoffs, and generate review-ready packets before opening PRs.

⚠️ Early and under active development. The surface is five focused MCP tools: get_work_state, claim_work, update_task, get_task_context, and handoff.

Why

Agents work well in isolation, but their plans, assumptions, and decisions only become visible at PR time. Teams hack around this today with AGENTS.md, handoff files, worktrees, and custom scripts. Concord packages the smallest useful version of that: a local place for agents to record what they are doing while they do it.

Install

npm install -g @concord-ai/concord-mcp
concord install

concord install writes Concord's tool instructions into your client configs (CLAUDE.md, AGENTS.md, .codex/, .cursor/rules/). Then register the MCP server with your client and let your agent use the tools through MCP. Per-client setup:

There is no universal /concord slash command — commands are client-specific. Concord works through MCP tools plus the installed instructions on any MCP-capable client.

The five tools

Tool	When	What it does
`get_work_state`	before choosing work	shows active tasks, overlaps, review-ready work, and open questions
`claim_work`	before editing	records the task + expected files/modules; flags overlaps with other active work
`update_task`	while working	appends typed intent, progress, decisions, questions, blockers, and findings
`get_task_context`	resuming or coordinating	returns the task, ordered updates, handoff, review evidence, and live overlaps
`handoff`	done, blocked, or pre-PR	captures evidence; `ready_for_review` also produces the review packet

What you get

SQLite is the local source of truth. concord init adds .concord/ to the repository's .gitignore, so the generated workspace stays local by default. Teams that want selected artifacts in PRs can remove that rule or force-add the human-readable files:

.concord/
├── concord.db          local source of truth
├── HANDOFF.md          human-readable handoff
├── REVIEW_PACKET.md    review-ready evidence
└── WORK_STATE.json     generated export (optional)

CLI

Agents use the MCP tools; humans use the CLI.

concord init                 # create the .concord/ workspace
concord status               # active work, overlaps, review-ready, open questions
concord tasks                # list all tracked tasks
concord handoff <task-id>    # print the latest handoff
concord review-packet <id>   # print the latest review packet
concord export markdown      # regenerate .concord/ artifacts
concord doctor               # workspace checks + per-task tool adoption

Try the demo

pnpm demo

Runs the two-agent overlap demo: two agents claim overlapping work, share and read task context, then one hands off and marks the task review-ready.

What this is / is not

Shared work-state and task memory for coding agents using the same local checkout. Not an orchestrator, code reviewer, hosted sync service, memory vector DB, or autonomous coding agent.

Contributing

See CONTRIBUTING.md and CLAUDE.md. This repo is strictly typed (no any, no typecasts), modular, and every PR stays under 600 LOC. Good first issues are labelled good first issue.

Star History

License

MIT