LaunchDarkly MCP Server
LaunchDarkly’s official MCP server for managing feature flags, targeting rules, AI Configs, and observability data through an AI client.
- Skill Road
- LaunchDarkly MCP Server
Description
The LaunchDarkly MCP Server is LaunchDarkly's official Model Context Protocol implementation, connecting MCP-capable AI clients such as Claude Code, Cursor, VS Code with GitHub Copilot, or Windsurf directly to the LaunchDarkly API. Instead of managing feature flags, targeting rules, or rollout percentages exclusively through the web dashboard, an agent can be instructed in plain language to create a flag, adjust a targeting rule, or check the status of a gradual rollout. The repository lives under the official launchdarkly GitHub organization, is licensed under MIT, and was last updated on September 24, 2026 — an actively maintained project run by LaunchDarkly itself rather than a community wrapper.
Hosted server recommended, local server for EU and Federal
LaunchDarkly offers the server in two official variants. The hosted server at https://mcp.launchdarkly.com/mcp/launchdarkly is, according to the provider, the recommended path: sign-in happens through OAuth consent rather than a hardcoded API key, and it is officially documented for Cursor, Claude Code, VS Code with GitHub Copilot, and Windsurf. For customers on an EU or Federal instance of LaunchDarkly, the hosted server is not available per the documentation — the provider explicitly points these customers to the self-managed local server from the same repository. That local server can run via npx, as a downloaded standalone binary for several platforms, from a cloned source checkout, or as a Docker image through the AWS Marketplace or an ECR registry. This entry treats both paths as a single server (deployment_type = both) because they come from the same official repository and expose the same tools.
Tools for feature flags, AI Configs, and observability
The server groups its tools into several resource categories. The Feature Flags area covers full lifecycle management: creating, reading, patching, and deleting flags, plus checking targeting rules and status per environment. AI Configs let an agent create and manage configurations for AI models and variations directly. The server additionally exposes the Audit Log for traceability, Code References to link flags to repositories, and Environments to list environments per project. According to the provider, observability tools are also included, letting an agent query logs, traces, error groups, and dashboard data through chat, alongside preconfigured "Agent Skills" for multi-step procedures such as flag cleanup with an automatic safety check before deletion.
Installation and authentication
For the hosted server, visiting the install page at https://mcp.launchdarkly.com/mcp/launchdarkly/install is often enough to connect without a manual configuration file; alternatively, the endpoint can be added manually to a client's MCP configuration. For the local server, the documented command is npx -y --package @launchdarkly/mcp-server -- mcp start --api-key <TOKEN>, where the API key is generated through the authorization page in the LaunchDarkly account and authenticates against https://app.launchdarkly.com (standard), https://app.launchdarkly.us (Federal), or https://app.eu.launchdarkly.com (EU) depending on the instance. For write access to feature flags, LaunchDarkly's own documentation recommends at minimum the Writer base role or the predefined Developer preset role, not an account with full administrator rights.
Cost and prerequisites
The MCP server's source code itself is free under the MIT license. The underlying LaunchDarkly platform offers, per its own pricing page, a permanently free Developer tier with unlimited seats and core features, alongside usage-based and individually negotiated Enterprise tiers for larger teams. A LaunchDarkly account with an appropriately scoped API key is required either way; current quotas and plan details should be checked on the official pricing page, since they can change.
Who benefits from the LaunchDarkly MCP Server
The server suits development teams that already manage feature flags, staged rollouts, or A/B tests through LaunchDarkly and want to handle recurring work — creating a new flag, adjusting a targeting rule, checking rollout progress, or cleaning up stale flags — directly from a coding agent instead of switching between editor and dashboard. It is especially useful for teams building AI-assisted deployment and release workflows who want flag changes tied closely to the surrounding code context. Anyone not using LaunchDarkly, or managing flags solely through their own internal tooling, gets no benefit from this server.
Security and limits
Because feature flags directly control the behavior of production applications, an agent using this server should get only the minimum necessary permissions — LaunchDarkly explicitly recommends a restricted role instead of full administrator rights. Write actions such as deleting flags or changing targeting rules in production environments should first be tested on non-critical flags or in a test environment before being applied more broadly. When running locally, treat the API key like any other access secret and avoid sharing it in plain text or committing it to a repository; the hosted server's OAuth consent flow handles this safeguard for you.
Requirements
An MCP-compatible AI client (e.g. Claude Code, Cursor, VS Code with GitHub Copilot, or Windsurf), a LaunchDarkly account with access to the target project, and for local use an API key with the Writer or Developer role.
Installation instructions
Quick start
Hosted (recommended): open the install page https://mcp.launchdarkly.com/mcp/launchdarkly/install and complete the OAuth consent flow, or add the endpoint manually to the client configuration. Local (e.g. for EU/Federal): run npx -y --package @launchdarkly/mcp-server -- mcp start --api-key <TOKEN> with an API key generated through the LaunchDarkly authorization page.
npx -y --package @launchdarkly/mcp-server -- mcp start --api-key <TOKEN>
Step 1: Decide before setup: hosted or local
LaunchDarkly offers the MCP server in two official variants. For standard instances, the provider recommends the hosted server at https://mcp.launchdarkly.com/mcp/launchdarkly, which needs no local installation and authorizes through OAuth consent. For EU or Federal instances, the hosted server is not available per the documentation; here the local, self-managed server via the @launchdarkly/mcp-server npm package is the documented path.
Step 2: Connect the hosted server (recommended)
The simplest way in is the install page at https://mcp.launchdarkly.com/mcp/launchdarkly/install, which connects the client without a manual configuration file. Alternatively, add the endpoint manually — in Cursor via Settings → MCP Tools → Custom MCP, in Claude Code via the claude mcp add command, or in Windsurf via the mcp_config.json file. After saving, the client opens an OAuth consent window; sign in with your LaunchDarkly account there and authorize access to the desired project.
claude mcp add
Step 3: Set up the local server (for EU/Federal or without OAuth access)
First, generate an API key with the Writer or Developer role — not full administrator rights — through the authorization page in your LaunchDarkly account. Then add the following to the client's MCP configuration:
{
"mcpServers": {
"launchdarkly": {
"command": "npx",
"args": [
"-y", "--package", "@launchdarkly/mcp-server", "--",
"mcp", "start", "--api-key", "<YOUR_API_KEY>"
]
}
}
}
For Federal or EU instances, the server must additionally authenticate against https://app.launchdarkly.us or https://app.eu.launchdarkly.com instead of the default https://app.launchdarkly.com; the specific environment variable for this is documented in the repository (RUNTIMES.md and the README). Standalone binaries from GitHub releases and a Docker image via AWS Marketplace or ECR are also available.
Step 4: Verify the connection with a read task
Before write actions such as creating or deleting a flag, run a harmless test request first, such as: "List all feature flags in project X." Once the expected project is correctly recognized, tasks like adjusting a targeting rule or checking the rollout status of a specific flag become reasonable next steps.
Keep permissions minimal
Because feature flags directly control the behavior of production applications, the API key or authorized account used should hold only the minimum necessary permissions. LaunchDarkly explicitly recommends the Writer base role or the predefined Developer preset role for this. Test write changes on non-critical flags or in a test environment first, before they affect production rollouts.
npx -y --package @launchdarkly/mcp-server -- mcp start --api-key <TOKEN>
Authentication
Hosted server: OAuth consent on connect. Local server: a personal LaunchDarkly API key passed via the --api-key parameter, scoped to the relevant instance (standard, Federal, or EU).
Required access permissions
LaunchDarkly recommends at minimum the Writer base role or the Developer preset role for write access, rather than full administrator rights.
Transmitted or stored data
The server returns flag, targeting, audit log, and observability data to the connected AI client, which may forward results to its model provider; review that provider’s data policy separately.
Security risks
Feature flags control the behavior of production applications. Test write changes on non-critical flags first, grant only the minimum necessary permissions, and treat the local API key like any other secret.
License and costs
- License
- MIT
- Cost
- free
The server code is free (MIT license). Per its own pricing page, LaunchDarkly offers a permanently free Developer tier alongside paid, usage-based, and individually negotiated Enterprise tiers. Check current details on the official pricing page.
Alternatives
Not recorded yet.
At a glance
- Provider
- LaunchDarkly
- Status
- Official server
- Deployment
- Local and remote
- Current version
- 0.6.2
- GitHub stars
- 27
- Last reviewed
- 24.09.2026
Repository and documentation
Categories
Supported clients
Not recorded yet.
Related guides
Guides and background related to this entry.