What it does

Manages Unleash feature toggles: list flags, read strategies, and flip state. The read path is the safe one and covers most of what an agent needs during a release. If you enable writes, scope the token to a project and keep the production toggle manual.

Install

Terminal

npx -y @unleash/mcp

Client configuration

Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.

mcp.json

{
  "mcpServers": {
    "unleash": {
      "command": "npx",
      "args": [
        "-y",
        "@unleash/mcp"
      ]
    }
  }
}

Use it for

Reading rollout state and toggling flags behind a review step

Skip it if

Write access without an approval flow, for the same reason as any flag tool

When to use it

Reach for this when the task needs feature-flags inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.

Other TypeScript servers

Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude

Unleash MCP