> For the complete documentation index, see [llms.txt](https://docs.natoma.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.natoma.ai/apps/launchdarkly.md).

# LaunchDarkly

**Type:** Official

**Source Type:** Repository

**Source:** [GitHub](https://github.com/launchdarkly/mcp-server)

**Description:** LaunchDarkly MCP server provides AI assistants with access to LaunchDarkly's feature management platform. It enables querying flags, projects, environments, segments, and audit history.

**Configuration Parameters:**

* **LaunchDarkly API Access Token** \* (sensitive) - Token from **Account settings → Authorization → Create token**.
* **LaunchDarkly Server URL** (optional) - Set only for EU/Federal instances (e.g. `https://app.eu.launchdarkly.com`).
* **LaunchDarkly Scope** (optional) - Optional scope hint (e.g. `read`).

**Setup Steps:**

1. Log in to LaunchDarkly.
2. Navigate to **Account settings → Authorization → Create token**.
3. Name the token and assign a role — `Reader` for read-only, or a custom role with narrower scope.
4. Copy the token and, when creating the connection in Natoma, paste it and save.
