concord-mcp

⚠️ Early and under active development. The public surface is five workflow tools covering presence, task memory, versioned ownership, and evidence-rich handoffs.

One workspace. Every agent.

Google Workspace gave human teams a shared place to see, create, and coordinate work. Concord brings that collaboration layer to coding agents — local-first, model-agnostic, and built around the repository.

Concord is not another autonomous agent. It is the shared workspace around your agents: presence, task memory, ownership, handoffs, and review state through one small MCP server.

Quick start

npm install -g @concord-ai/concord-mcp
cd /path/to/your/repository
concord setup

concord setup creates the local .concord/ workspace, registers the MCP server (.mcp.json, .cursor/mcp.json, and Codex's ~/.codex/config.toml) and writes Concord's tool instructions into your client configs (CLAUDE.md, AGENTS.md, .codex/, .cursor/rules/). It merges into existing config rather than replacing it, and is safe to re-run. Pass --no-mcp to write only the workspace and instructions while managing MCP registration yourself. Restart your client afterwards so it picks up the new server.

In an interactive terminal, setup detects Codex, Claude, and Cursor and asks once whether to enable their live-prompt integrations. Use concord setup --agent-comms to approve them non-interactively.

• Claude Code
• Codex
• Cursor

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.

Upgrade

When a new Concord version is available, update the global package and confirm the installed version:

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

Concord does not auto-update. Upgrading preserves each repository's local .concord/ workspace; any required database migrations run automatically when the workspace is next opened. The interactive concord CLI checks npm at most once per day and prints an update command when a newer stable release is available. Set CONCORD_NO_UPDATE_CHECK=1 to disable this best-effort check.

The tools

Writes accept an agent_id, which keeps presence live just by working. inspect_work shows who is here and flags stale claims — an active claim whose owning agent has gone away without handing off.

For live agent-to-agent communication, run concord setup --agent-comms (or accept the one-time interactive setup prompt), then restart existing client sessions once. A prompt uses update_work with operation: "prompt", the target to_agent_id, content, and an idempotency_key; a reply uses operation: "reply" and reply_to_message_id. Busy targets are steered into their current turn, while idle targets start a new turn. Delivery fails immediately when the named agent has no reachable relay; Concord does not silently reroute it.

Concord resolves the repository workspace automatically. Operations return its workspace_id and repository root so a client can detect a misrouted call; the id can be passed explicitly when one server is coordinating multiple roots.

Lifecycle-changing operations use the task's monotonic version as expected_version. If two agents act on the same version, only the first transition succeeds. Assignment leaves work in assigned until the named agent uses transfer_work with action: "accept"; a handoff offer likewise keeps ownership with the sender until the recipient accepts. Every ownership change is retained in an append-only audit history.

Migrating from the granular surface

The five tools replace the earlier public names; there are no legacy aliases. Update the package and re-run concord setup to refresh generated instructions. concord doctor reports stale instruction blocks.

What you get

SQLite is the local source of truth, kept in the .concord/ at the root of the repo the work is happening in. The MCP server resolves that root from CONCORD_REPO_ROOT if set, then Claude Code's CLAUDE_PROJECT_DIR (which Claude Code sets automatically, even for a user-scoped server), then its working directory — so every agent in one repo shares one store. Set CONCORD_REPO_ROOT when running the server somewhere its working directory is not inside the repo.

Linked Git worktrees follow Git's commondir metadata to the primary checkout, so the main checkout and all linked worktrees intentionally share one Concord database and workspace id.

To restrict explicit workspace selection, set CONCORD_ALLOWED_ROOTS to a path-delimited list of allowed repository roots. Without an allowlist, decoded roots must still exist and be directories.

concord setup 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

Concord supports both typed MCP tools and a regular CLI. MCP-capable agents can call the tools directly; humans and CLI-oriented agents can work with the same shared workspace through concord commands.

concord setup                # set up local state, instructions, and MCP clients
concord status               # roster, active work, overlaps, stale claims, review-ready
concord dashboard            # live, keyboard-driven view of agents, tasks, alerts, and activity
concord who                  # which agents are present and what they