Coordinate multiple AI agents working on the same codebase simultaneously with a lightweight synchronization layer. Built for teams running parallel AI workflows that need to avoid conflicts and share context.
io.github.cyanheads/shift-mcp-server
Local install
STDIO
No auth required
How models use it and what it is built for.
Coordinate multiple AI agents working on the same codebase simultaneously with a lightweight synchronization layer. Built for teams running parallel AI workflows that need to avoid conflicts and share context.
Local install — runs as a subprocess.
Configuration this server reads at startup.
Sets the minimum log level for output (e.g., 'debug', 'info', 'warn').
The hostname for the HTTP server.
The port to run the HTTP server on.
The endpoint path for the MCP server.
Authentication mode to use: 'none', 'jwt', or 'oauth'.
Sets the minimum log level for output (e.g., 'debug', 'info', 'warn').
Where to find authoritative docs and source for Cyanheads Shift.
Paste any of these into Agent Studio after connecting Cyanheads Shift.
Common questions about connecting and running Cyanheads Shift.
What is Shift MCP server used for?
Shift is a coordination layer that lets multiple AI agents work on the same codebase without stepping on each other's toes. It synchronizes agent actions and manages shared context across parallel workflows.
How do I set up authentication for Shift?
Shift supports three authentication modes via the MCP_AUTH_MODE environment variable: 'none' (no auth), 'jwt' (JSON Web Tokens), and 'oauth' (OAuth 2.0). Choose based on your security requirements and deployment environment.
How do I configure the HTTP server for Shift?
Use MCP_HTTP_HOST to set the hostname, MCP_HTTP_PORT for the port number, and MCP_HTTP_ENDPOINT_PATH to define the endpoint path. These let you customize where and how the coordination server listens.
What logging options are available?
Set MCP_LOG_LEVEL to control verbosity: 'debug' for detailed output, 'info' for standard logs, or 'warn' for warnings and errors only. This helps troubleshoot multi-agent coordination issues.
Can I run Shift in a containerized or cloud environment?
Yes. All configuration is environment-variable driven (host, port, auth mode, logging), making it suitable for Docker, Kubernetes, and cloud deployments. Set the variables in your deployment manifest or secrets manager.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams