mcp-configure
launchdarkly/agent-skills
Configure LaunchDarkly's hosted MCP server for feature flag management in your coding agent.
What is mcp-configure?
Sets up the LaunchDarkly MCP server during onboarding so your agent can manage feature flags via MCP tools. Use this when the parent LaunchDarkly onboarding skill reaches Step 4. Supports Cursor, Claude Code, Windsurf, GitHub Copilot, and other MCP-compatible agents with OAuth authentication.
- Detects your coding agent (Cursor, Claude Code, Windsurf, GitHub Copilot, VS Code) and configures the unified LaunchDarkly MCP server
- Provides quick-install links and manual config templates for each agent type
- Handles OAuth authentication with no API keys required for the hosted server
- Verifies MCP connectivity by probing feature flag tools after setup
- Detects and migrates deprecated MCP configurations to the unified server
- Falls back to ldcli/API if MCP setup fails, without blocking onboarding
How to install mcp-configure
npx skills add https://github.com/launchdarkly/agent-skills --skill mcp-configure- A LaunchDarkly account (sign up at https://app.launchdarkly.com/signup?source=agent)
- An MCP-compatible coding agent (Cursor, Claude Code, Windsurf, GitHub Copilot, or VS Code)
How to use mcp-configure
- 1.Detect your coding agent type from the parent onboarding skill or let the skill infer it from your environment
- 2.Click the quick-install link: https://mcp.launchdarkly.com/mcp/launchdarkly/install and watch your editor for an approval dialog or MCP server prompt
- 3.If quick install doesn't work, manually add the LaunchDarkly MCP server entry to your agent's config file (e.g., .cursor/mcp.json for Cursor, .mcp.json for Claude Code)
- 4.Enable the LaunchDarkly server in your editor's MCP settings and complete OAuth authorization
- 5.The skill will probe MCP tools to verify connectivity; if it fails, restart your editor and resume onboarding
Use cases
- Complete LaunchDarkly onboarding in a coding agent by configuring MCP at Step 4
- Enable feature flag management tools in Cursor or Claude Code without manual API key setup
- Migrate from deprecated local MCP servers to the unified hosted LaunchDarkly server
- Verify MCP connectivity and troubleshoot configuration issues during agent setup
- Developers setting up LaunchDarkly in Cursor, Claude Code, Windsurf, or GitHub Copilot
- Teams using MCP-compatible coding agents who want feature flag management integrated
- Users migrating from older LaunchDarkly MCP configurations to the unified hosted server
mcp-configure FAQ
No. The hosted LaunchDarkly MCP server uses OAuth authentication, so no API keys are required.
The skill will fall back to manual configuration. It will provide the exact JSON config for your agent type and guide you through adding it to your config file.
The skill will detect deprecated configurations and ask if you want to migrate to the unified mcp/launchdarkly server. You can accept the migration or keep the old config.
The skill will suggest restarting your editor. If that doesn't help, it will fall back to ldcli or API for the remaining onboarding steps without blocking progress.
Cursor, Claude Code, Windsurf, GitHub Copilot, and VS Code (when applicable). The skill detects your agent and provides agent-specific setup instructions.
Full instructions (SKILL.md)
Source of truth, from launchdarkly/agent-skills.
name: mcp-configure description: "Configure the LaunchDarkly hosted MCP server during onboarding. Use when the parent LaunchDarkly onboarding skill reaches Step 4 (MCP). Supports Cursor, Claude Code, Windsurf, GitHub Copilot, and other MCP-compatible agents. OAuth authentication; no API keys for the hosted server." license: Apache-2.0 compatibility: Requires an MCP-compatible coding agent and a LaunchDarkly account metadata: author: launchdarkly version: "0.1.0"
LaunchDarkly MCP Server Configuration (onboarding)
Configures the LaunchDarkly hosted MCP server so flag management skills and onboarding can use MCP tools. Uses OAuth for authentication — no API keys needed for the hosted server.
This skill is nested under LaunchDarkly onboarding; the parent skill's Step 4 hands off here. Hosted MCP is the default and the only supported option for this onboarding flow.
Prerequisites
- A LaunchDarkly account (sign up at the resolved signup URL — see Source Attribution in the parent skill; default:
https://app.launchdarkly.com/signup?source=agent) - An MCP-compatible coding agent
Hosted MCP Server
LaunchDarkly provides a unified hosted MCP server that handles feature management, AgentControl, and other LaunchDarkly capabilities.
| Server | URL | Purpose |
|---|---|---|
| LaunchDarkly | https://mcp.launchdarkly.com/mcp/launchdarkly | Feature flags, AgentControl, and more |
Workflow
Step 1: Detect the Agent
If the parent onboarding skill already identified the agent, use that context. Otherwise infer from agent-specific directories, config files, and the tools available to you at runtime. Do not ask the user — pick the strongest match.
Step 2: Try Quick Install
The fastest path is the quick install link. Present it to the user:
LaunchDarkly MCP: https://mcp.launchdarkly.com/mcp/launchdarkly/install
Important: tell the user what to expect after clicking the link. The install link may open in the browser, but the authorization or "add server" prompt typically appears back in the coding environment (the editor or host app where the agent runs), not in the browser. Immediately after presenting the link, include guidance like:
- After clicking the link, watch your coding environment (the editor where this conversation is running) for an approval dialog, an "add MCP server" prompt, or a tools/integrations panel notification.
- The browser may start the OAuth flow, but you'll likely need to confirm or approve the server in the editor itself.
- If no prompt appears: check the editor's MCP, integrations, or tools settings area to see if the server was added but needs to be enabled. If it's not there at all, fall back to manual setup (Step 3 below).
If the quick install link doesn't work (agent doesn't support it, or user prefers manual setup), proceed to Step 3.
Step 3: Manual Configuration
Locate the MCP config file for the detected agent and add the hosted server entry. See MCP Config Templates for the exact JSON per agent.
| Agent | Config file location |
|---|---|
| Cursor | .cursor/mcp.json (project) or global Cursor settings |
| Claude Code | .mcp.json (project) or ~/.claude.json (global) |
| GitHub Copilot | Repo Settings on GitHub.com → Copilot → Cloud agent → MCP (see MCP UI links) |
| Windsurf | Agent-specific MCP config |
The unified server handles both feature management and AgentControl, so only one server entry is needed.
Step 4: Agent-Specific Authorization
After writing the config, some agents need extra steps. Do not send users through long manual menu paths only—use MCP UI links (HTTPS docs + command: shortcuts for VS Code / Cursor).
Cursor:
- Open MCP in Cursor using the Cursor MCP doc link and in-app shortcuts (e.g. Settings search via
command:link when clickable). - Toggle on LaunchDarkly (or the name from your config).
- Click Connect to authorize with the LaunchDarkly account.
VS Code (when applicable):
- Use VS Code MCP doc +
mcp.json/ Settings links; trust or start the server if prompted.
Claude Code:
- Authorization happens automatically on first MCP tool call via OAuth prompt. File-based setup: Claude Code MCP doc.
GitHub Copilot:
- Click Save after adding the MCP configuration in repo settings. Use the GitHub Copilot MCP doc for the exact Settings path on github.com.
Step 5: Enable and Verify
After adding the config, the user needs to enable and authorize the server. MCP tools may become available immediately in some agents (Cursor, Claude Code) without a restart.
- Tell the user to enable the server. They need to toggle on the LaunchDarkly server and complete OAuth in their editor's MCP settings (e.g. in Cursor: toggle on the server and click Connect).
- Probe immediately. After the user confirms they've enabled the server, call a lightweight MCP tool (e.g.
list-feature-flagswith the known project key). Do not ask the user whether MCP is working — just try it.- Success (normal response, even an empty flag list): MCP is live. Note it in the onboarding log and continue.
- Failure (tool not found, auth error, timeout): update the onboarding log first (set Step 4 to "in progress - pending restart", Next step to "Step 4: Verify MCP after restart"), then suggest a restart with clear resume instructions:
"MCP tools aren't available yet. Try restarting your editor. When you come back, just say 'continue LaunchDarkly onboarding' — I'll pick up where we left off using the onboarding log."
- If restart doesn't help, fall back to ldcli/API for Steps 5-6. Note the fallback in the onboarding log. Do not block the rest of onboarding.
- If the failure looks like a config issue (wrong file path, missing OAuth, server not enabled), mention the likely cause so the user can fix it on their own time — but do not block progress.
Edge Cases
- User already has MCP configured: Verify by checking for existing LD MCP entries in the config.
-
mcp/launchdarkly→ working, skip configuration -
mcp/fmormcp/aiconfigs→ deprecated, ask before migrating:D-MIGRATE -- BLOCKING: Call your structured question tool now.
- question: "I see you have a deprecated MCP server configured (
mcp/fmand/ormcp/aiconfigs). Those endpoints are deprecated — the unified server atmcp/launchdarklynow handles both feature management and AgentControl. Want me to update your config?" - options:
- "Yes, update my config to use the unified server"
- "No, leave it as is for now"
- STOP. Do not modify the MCP config before the user selects an option.
If they agree, remove the deprecated entries and ensure the unified
mcp/launchdarklyconfig is present. See MCP Config Templates. If they decline, note the deprecation and continue. - question: "I see you have a deprecated MCP server configured (
-
- User has the old npx-based local server: Migrate them. Remove the old
npx @launchdarkly/mcp-serverentry and anyLD_ACCESS_TOKENenv vars. Replace with the hosted server config. See MCP Config Templates — Migration. - Agent not in known list: Provide the generic pattern: the user needs to add an MCP server entry pointing to
https://mcp.launchdarkly.com/mcp/launchdarklyusing whatever format their agent expects. - User opts out of MCP during onboarding: Document that choice and continue with the parent skill's ldcli/API fallbacks for environments and flags; do not block SDK work.
What NOT to Do
- Don't configure the old npx-based local server. Use the hosted server.
- Don't ask for or store API keys for the hosted server. The hosted server uses OAuth.
- Don't configure the old separate FM/AgentControl servers. Use the unified
mcp/launchdarklyserver.
References
- MCP UI links — HTTPS +
command:links to open MCP settings (Cursor, VS Code, Claude Code, Windsurf, GitHub) - MCP Config Templates — hosted OAuth JSON per agent; migration from old configurations
- Official MCP docs — full hosted setup guide
Related skills
More from launchdarkly/agent-skills and the wider catalog.

migrate
Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move the tools, add tracking, attach evaluators. Use when the user wants to externalize model/prompt configuration, move from direct provider calls (OpenAI, Anthropic, Bedrock, Gemini, Strands) to a managed config, or stage a full hardcoded-to-LaunchDarkly migration.

first-flag
Create and toggle your first LaunchDarkly feature flag end-to-end with evaluation code.

online-evals
Attach judges to config variations for automatic LLM-as-a-judge evaluation. Create custom judges, configure sampling rates, and monitor quality scores.

plan
Generate a minimal LaunchDarkly SDK integration plan from your detected stack.

projects
Guide for setting up LaunchDarkly projects in your codebase. Helps you assess your stack, choose the right approach, and integrate project management that makes sense for your architecture.

sdk-install
Install and initialize the correct LaunchDarkly SDK by running detect, plan, and apply in sequence.