LaunchDarkly Model Context Protocol Server
by
Provides a Model Context Protocol server that enables AI clients to read and modify LaunchDarkly feature flags and AI Configs directly from their workflows.
LaunchDarkly Model Context Protocol Server Overview
What is LaunchDarkly Model Context Protocol Server about?
The server implements the Model Context Protocol (MCP) for LaunchDarkly, exposing endpoints that allow AI‑enabled tools to list, create, update, and delete feature flags and AI Configs within a LaunchDarkly project.
How to use LaunchDarkly Model Context Protocol Server?
- Install the server via npx (recommended) or by downloading a standalone binary.
- Supply a LaunchDarkly API key (found on the Authorization page) either as a command‑line argument (
--api-key) or via theAPI_KEYenvironment variable. - Optionally specify a custom
--server-urlto target non‑default environments (Federal, EU, etc.). - Configure your AI client (Cursor, Claude, Qodo Gen, etc.) to reference the MCP server definition.
Key features of LaunchDarkly Model Context Protocol Server
- Supports both featureFlags and aiConfigs resources with full CRUD operations.
- Multiple installation methods: npx, standalone binary, local source clone.
- Environment‑aware via
--server‑urlflag. - Works with any AI client that understands MCP, requiring no additional runtime beyond a supported JavaScript runtime.
Use cases of LaunchDarkly Model Context Protocol Server
- AI‑driven feature flag management: let LLMs suggest flag changes based on user data.
- Automated rollout testing: AI agents can programmatically create variations and evaluate performance.
- CI/CD integration: pipelines can invoke MCP calls to adjust flags before deployments.
- Custom AI assistants: embed flag and config queries into chat‑based tools used by product teams.
FAQ from the LaunchDarkly Model Context Protocol Server
Q: Which runtimes are supported?
A: See RUNTIMES.md in the repository; the server runs on Node.js, Bun, and other JavaScript runtimes listed there.
Q: Do I need to build the server from source?
A: No. The preferred method is npx which pulls the package on‑demand. A pre‑built binary is also available via GitHub releases.
Q: How do I target a non‑commercial LaunchDarkly environment?
A: Add the --server-url argument with the appropriate URL (e.g., https://app.launchdarkly.us for Federal).
Q: Can I store the API key securely?
A: Yes. Instead of hard‑coding the key in the command, set it in the API_KEY environment variable and reference it in the args.
Q: Is the server compatible with Terraform? A: The repository is managed by Terraform, but the MCP server itself is independent; you can provision it alongside Terraform‑managed resources.
LaunchDarkly Model Context Protocol Server's README
LaunchDarkly's Model Context Protocol (MCP) Server
The official Model Context Protocol (MCP) server for LaunchDarkly.
Table of Contents
Installation
This MCP server can be installed in any AI client that supports the MCP protocol. Refer to your AI client's instructions if it isn't listed here.
Cursor installation steps
Create a .cursor/mcp.json file in your project root with the following content:
{
"mcpServers": {
"LaunchDarkly": {
"command": "npx",
"args": [
"-y", "--package", "@launchdarkly/mcp-server", "--", "mcp", "start",
"--api-key", "api-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
]
}
}
}
Specify your API key as found on LaunchDarkly's Authorization page.
Claude installation steps
Add the following server definition to your claude_desktop_config.json file:
{
"mcpServers": {
"LaunchDarkly": {
"command": "npx",
"args": [
"-y", "--package", "@launchdarkly/mcp-server", "--", "mcp", "start",
"--api-key", "api-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
]
}
}
}
Specify your API key as found on LaunchDarkly's Authorization page.
Qodo Gen installation steps
- Open Qodo Gen chat panel in VSCode or IntelliJ.
- Click
Connect more tools. - Click
+ Add new MCP. - Add the following configuration:
{
"mcpServers": {
"LaunchDarkly": {
"command": "npx",
"args": [
"-y", "--package", "@launchdarkly/mcp-server", "--", "mcp", "start",
"--api-key", "api-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
]
}
}
}
Specify your API key as found on LaunchDarkly's Authorization page.
- Click
Save.
Standalone binary installation steps
You can also run the MCP server as a standalone binary with no additional dependencies. You must pull these binaries from available GitHub releases while specifying the appropriate tag value:
curl -L -o mcp-server https://github.com/launchdarkly/mcp-server/releases/download/{tag}/mcp-server-bun-darwin-arm64 && \
chmod +x mcp-server
Installation steps from a local clone
You can also run the MCP server locally by cloning this repository. Once cloned, you'll need to install dependencies (npm install) and build the server (npm run build).
Then, configure your server definition to reference your local clone. For example:
{
"mcpServers": {
"launchdarkly": {
"command": "node",
"args": [
"/path/to/mcp-server/bin/mcp-server.js", "start",
"--api-key", "api-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
]
}
}
}
Requirements
For supported JavaScript runtimes, please consult RUNTIMES.md.
Available Resources and Operations
aiConfigs
- getTargeting - Show an AI Config's targeting
- updateTargeting - Update AI Config targeting
- list - List AI Configs
- create - Create new AI Config
- delete - Delete AI Config
- get - Get AI Config
- update - Update AI Config
- createVariation - Create AI Config variation
- deleteVariation - Delete AI Config variation
- getVariation - Get AI Config variation
- updateVariation - Update AI Config variation
featureFlags
- list - List feature flags
- create - Create a feature flag
- get - Get feature flag
- patch - Update feature flag
- delete - Delete feature flag
Available Environments
Most customer accounts run on LaunchDarkly's commercial (default) environment. Customers on other environments can specify the --server-url argument to connect to the appropriate environment. For example, customers on LaunchDarkly's Federal environment should specify the --server-url https://app.launchdarkly.us argument when starting their MCP server.
| Environment | Server URL |
|---|---|
| Commercial (Default) | https://app.launchdarkly.com |
| Federal | https://app.launchdarkly.us |
| EU | https://app.eu.launchdarkly.com |
Contributions
While we value open-source contributions to this SDK, this library is generated programmatically. Any manual changes added to internal files will be overwritten on the next generation. We look forward to hearing your feedback. Feel free to open a PR or an issue with a proof of concept and we'll do our best to include it in a future release.
About LaunchDarkly
- LaunchDarkly is a continuous delivery platform that provides feature flags as a service and allows developers to iterate quickly and safely. We allow you to easily flag your features and manage them from the LaunchDarkly dashboard. With LaunchDarkly, you can:
- Roll out a new feature to a subset of your users (like a group of users who opt-in to a beta tester group), gathering feedback and bug reports from real-world use cases.
- Gradually roll out a feature to an increasing percentage of users, and track the effect that the feature has on key metrics (for instance, how likely is a user to complete a purchase if they have feature A versus feature B?).
- Turn off a feature that you realize is causing performance problems in production, without needing to re-deploy, or even restart the application with a changed configuration file.
- Grant access to certain features based on user attributes, like payment plan (eg: users on the ‘gold’ plan get access to more features than users in the ‘silver’ plan).
- Disable parts of your application to facilitate maintenance, without taking everything offline.
- LaunchDarkly provides feature flag SDKs for a wide variety of languages and technologies. Read our documentation for a complete list.
- Explore LaunchDarkly
- Sign up for a free LaunchDarkly account
- launchdarkly.com for more information
- launchdarkly.com/docs for our documentation and SDK reference guides
- launchdarkly.com/docs/api for our API documentation
- blog.launchdarkly.com for the latest product updates
LaunchDarkly Model Context Protocol Server Reviews
Login Required
Please log in to share your review and rating for this MCP.
Actions
LaunchDarkly Model Context Protocol Server's Information
- Author
- launchdarkly
- Category
- Development Tools
- Language
- TypeScript
- License
- MIT License
- Version
- v0.4.0
- Stars
- 13
- Updated
- 1 month ago
Configuration
{
"mcpServers": {
"LaunchDarkly": {
"command": "npx",
"args": [
"-y",
"--package",
"@launchdarkly/mcp-server",
"--",
"mcp",
"start",
"--api-key",
"<YOUR_API_KEY>"
],
"env": {
"API_KEY": "<YOUR_API_KEY>"
}
}
}
}Claude Code (Terminal)
claude mcp add LaunchDarkly npx -y --package @launchdarkly/mcp-server -- mcp start --api-key <YOUR_API_KEY>Configure Clients
Similar MCP Servers like LaunchDarkly Model Context Protocol Server
Explore related MCPs that share similar capabilities and solve comparable challenges
Zed
OfficialClientby zed-industries
A high‑performance, multiplayer code editor designed for speed and collaboration.
Everything
Officialby modelcontextprotocol
Model Context Protocol Servers
Git
Officialby modelcontextprotocol
A Model Context Protocol server for Git repository interaction and automation.
Time
Officialby modelcontextprotocol
A Model Context Protocol server that provides time and timezone conversion capabilities.
Cline
OfficialClientby cline
An autonomous coding assistant that can create and edit files, execute terminal commands, and interact with a browser directly from your IDE, operating step‑by‑step with explicit user permission.
Continue
OfficialClientby continuedev
Enables faster shipping of code by integrating continuous AI agents across IDEs, terminals, and CI pipelines, offering chat, edit, autocomplete, and customizable agent workflows.
Context7 MCP
Officialby upstash
Provides up-to-date, version‑specific library documentation and code examples directly inside LLM prompts, eliminating outdated information and hallucinated APIs.
GitHub MCP Server
by github
Connects AI tools directly to GitHub, enabling natural‑language interactions for repository browsing, issue and pull‑request management, CI/CD monitoring, code‑security analysis, and team collaboration.
Daytona
by daytonaio
Provides a secure, elastic infrastructure that creates isolated sandboxes for running AI‑generated code with sub‑90 ms startup, unlimited persistence, and OCI/Docker compatibility.