Overview

Coordination layer for multiple AI agents working on the same codebase at once. Check in with a gist of your task and the files you expect to touch, see the full roster of active peers, and check out when finished — all from any MCP client. Runs as a stdio process or a local Streamable HTTP server.

Tools

Resources

The same roster is returned inline by shift_check_in; subscribers to shift://status also receive notifications/resources/updated on every check-in, session update, and check-out.

Capability reference

shift_check_in _tool

• Required gist plus optional files and workerId (6-char uppercase alphanumeric from an earlier check-in) to update a session.
• Returns your session and activeWorkers. Updates preserve omitted files and the original checkedInAt.
• An unknown workerId fails with reason unknown_worker (NotFound), a recovery hint, and the current roster.

shift_check_out _tool

• Required workerId (6-char uppercase alphanumeric), optional one-sentence summary
• Idempotent — an unknown or already-checked-out workerId succeeds silently rather than erroring
• Notifies shift://status subscribers only when a session actually existed and was removed

shift://status _resource

• Returns text/markdown — the active-workers table, or "No agents are currently active." when the roster is empty
• workerId comes from shift_check_in
• Updates push via notifications/resources/updated on every check-in, session update, and check-out

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.

Coordination-specific:

• In-memory worker session store — no database, no filesystem writes, cleared on restart
• The coordination protocol ships in every check-in response, so ground rules reach the agent without client-side configuration
• The active-workers table rides along with every check-in for situational awareness
• Patch semantics on session updates — only the fields provided change

Agent-friendly output:

• Both client surfaces carry the same data — structuredContent from the output schema, markdown from format()
• shift_check_in declares a typed error contract, so an unknown worker ID arrives with data.reason and a recovery hint
• Failure responses embed the current roster, so an agent recovers in the same turn instead of calling again to orient

Getting started

Add the following to your MCP client configuration file:

{
  "mcpServers": {
    "shift-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/shift-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "shift-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/shift-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "shift-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "MCP_TRANSPORT_TYPE=stdio",
        "ghcr.io/cyanheads/shift-mcp-server:latest"
      ]
    }
  }
}

Every agent sharing a codebase must reach the same server process for the roster to be shared. Over stdio each client spawns its own process, so point concurrent agents at one Streamable HTTP instance instead:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

• Bun v1.4.2 or higher (or Node.js v24+).
• No API keys, accounts, or external services.

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/shift-mcp-server.git

2. Navigate into the directory:

cd shift-mcp-server

3. Install dependencies:

bun install

4. Configure environment:

cp .env.example .env
# edit .env if you need to override a framework default

Configuration

No server-specific environment variables. Framework defaults worth knowing:

See .env.example for the full list of optional overrides.

Running the server

Local development

• Build and run:

  sh

  bun run rebuild
  bun run start:stdio
  # or
  bun run start:http
  

• Run checks and tests:

  sh

  bun run devcheck   # Lint, format, typecheck, security, packaging
  bun run test       # Vitest suites: unit, smoke, integration, fuzz
  bun run lint:mcp   # Validate MCP definitions against spec
  

Docker

docker build -t shift-mcp-server .
docker run --rm -p 3010:3010 shift-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/shift-mcp-server. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

Development guide

See CLAUDE.md/AGENTS.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic
• Use ctx.log for request-scoped logging, ctx.state for tenant-scoped storage
• Register new tools and resources in src/index.ts
• format() must render every field in the output schema — both client surfaces carry the same data

Contributing

Issues are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.