LaunchDarkly
Let AI assistants interact with your LaunchDarkly workspace.
LaunchDarkly
Let AI assistants interact with your LaunchDarkly workspace. With Lunar.dev MCPX, the MCP Gateway for secure and governed tool access, you connect the LaunchDarkly MCP server to Claude, ChatGPT, Cursor, and any MCP client through one gateway that routes, authenticates, and governs every LaunchDarkly tool call against your policies.
Why MCPX
MCPX is Lunar.dev's MCP Gateway. It sits between your AI agents and your MCP servers as a single gateway for every tool call, routing, authenticating, and governing traffic against your policies. Connect LaunchDarkly once and govern it everywhere: role-based access per agent with on-behalf-of attribution, real-time visibility, and an immutable audit trail of who did what, all deployable inside your own VPC.
Tools content
- create-ai-config · Write
Creates a new AI Config within a project. Useful for setting up LLM configurations programmatically. - create-ai-config-variation · Write
Adds a new variation to an AI Config, supporting experimentation or multi-model strategies. - delete-ai-config · Write
Deletes an AI Config and its associated variations. Intended for cleanup or deprecation workflows. - delete-ai-config-variation · Write
Deletes an AI Config variation. - get-ai-config · Read-only
Retrieves details of a specific AI Config, including variations and model settings. - get-ai-config-targeting · Read-only
Retrieves the targeting details of a specific AI Config, including individual targets, rules, and rollouts. - get-ai-config-variation · Read-only
Retrieves an AI configuration variation. - list-ai-configs · Read-only
Retrieves AI configuration settings for a specific project. This endpoint allows agents to access and modify AI-related configurations, ensuring that the AI's behavior aligns with project requirements and user expectations. - update-ai-config · Write
Updates metadata or configuration of an existing AI Config. - update-ai-config-targeting · Write
Updates the targeting of an existing AI Config. - update-ai-config-variation · Write
Updates a specific variation within an AI Config. Enables fine-tuned control of model behavior. - get-audit-log-entries · Read-only
Fetches audit log entries for a LaunchDarkly account. Use the `spec` parameter with format `proj/<projectKey>:env/<envKey>:flag/<flagKey>` to query a specific flag's change history (use `env/*` for all environments). - get-code-references · Read-only
Identifies which repositories have code references to a given flag, helping agents determine if they're operating on the correct repository and understand the scope of cleanup (single vs multi-repo). - get-environments · Read-only
Identifies which environments exist in a project and determines which are marked as "critical" (production, staging, etc.). Allows agents to programmatically identify critical environments instead of hardcoding assumptions. - create-feature-flag · Write
Creates a new feature flag within a project. AI agents can use this operation to define feature toggles for controlled rollouts, experimentation, or gated features, automating the flag setup process. - delete-feature-flag · Write
Removes a feature flag from the project. Used by AI agents to clean up deprecated toggles that are no longer in use, improving system hygiene and maintainability. - get-feature-flag · Read-only
Fetches the full configuration for a specific feature flag, including environments, variations, and targeting rules. Useful for agents auditing or managing specific feature toggles in a detailed, contextual manner. - get-flag-status-across-environments · Read-only
Returns lifecycle status (new, active, inactive, launched) based on actual usage patterns, evaluation counts, and configuration stability. This is the key intelligence for removal readiness assessment. - list-feature-flags · Read-only
Retrieves all feature flags within a project, including metadata and targeting rules. Enables AI agents to enumerate existing flags for inspection, configuration analysis, or generating flag usage reports across environments. - update-feature-flag · Write
Updates the configuration of an existing feature flag. Enables agents to change targeting rules, modify variations, or adapt rollout strategies dynamically in response to user behavior or experiment results.
Frequently asked questions
What is the LaunchDarkly MCP server?
Let AI assistants interact with your LaunchDarkly workspace. Through Lunar.dev MCPX, LaunchDarkly connects to any MCP-compatible AI client behind a single governed gateway.
How do I connect LaunchDarkly to MCPX?
Add the LaunchDarkly server in the MCPX control plane or your app.yaml, then point your AI client at your MCPX gateway. MCPX handles API Key and routes every LaunchDarkly call through the gateway.
Is the LaunchDarkly MCP server official?
LaunchDarkly is a community-maintained MCP server. MCPX lets you risk-assess and sandbox it before rolling it out to your teams.
What authentication does LaunchDarkly use with MCPX?
LaunchDarkly uses API Key. MCPX enforces authentication at the gateway with token-based auth, OAuth, and role-based profiles, so you control which agents can invoke it.
How many tools does LaunchDarkly expose in MCPX?
LaunchDarkly exposes 7 tools. In MCPX you can enable or disable each tool per agent for least-privilege access.
