Flags, AI Configs & metrics
Manage LaunchDarkly feature flags, AgentControl Configs (AI agent prompts/models), experiments, guarded and automated rollouts, segments, metrics, dashboards, alerts, and observability data (logs, traces, errors, sessions) directly from chat. Create and target flags, run and analyze experiments, configure AI agent prompts and tools, build dashboards and alerts, and investigate production issues without leaving the conversation.
MCP connector Server URL https://mcp.launchdarkly.com/mcp/launchdarklyCopy Login OAuth Tools Reads data88 check- check- find- find- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- get- list- list- list- list- list- list- list- list- list- list- list- list- list- list- list- list- list- list- list- list- list- list- list- list- list- list- list- list- list- match- preview- query- query- query- query- query- query- query- query- query- search- search-
Changes data36 clone- create- create- create- create- create- create- create- create- create- create- create- create- create- create- create- create- create- create- create- create- create- create- invite- link- run- setup- start- update- update- update- update- update- update- update- vent
Deletes or can't be undone45 apply- apply- archive- copy- delete- delete- delete- delete- delete- delete- delete- delete- delete- delete- delete- delete- delete- manage- restrict- save- start- stop- stop- toggle- toggle- toggle- unrestrict- update- update- update- update- update- update- update- update- update- update- update- update- update- update- update- update- update- update-
Skills 38 in the ChatGPT listing
Agent graphs Create and manage agent graphs — directed graphs of configs connected by edges with handoff logic. Alert investigation Investigates a triggered observability alert and returns a structured diagnosis with likely cause, scope, and next steps. apply Apply LaunchDarkly SDK onboarding: install dependency (or dual-SDK pair), configure env and secrets with consent, add init at entrypoint(s), verify compile. Built in metrics Instrument an existing codebase with LaunchDarkly config tracking. Configs create Create and configure configs in LaunchDarkly. Configs targeting Configure config targeting rules to control which variations serve to different users. Configs update Update, archive, and delete LaunchDarkly configs and their variations. Configs variations Experiment with configs by creating and managing variations. Create fix pr Investigates a root cause and files a minimal fix PR for a reported bug or observability finding. Create graph Creates observability dashboards and graphs from logs, traces, errors, sessions, metrics, and events data by previewing charts inline and saving them to a dashboard. Custom metrics Create, track, retrieve, update, and delete custom business metrics for configs. detect Detect repository stack for LaunchDarkly SDK onboarding: languages, frameworks, package managers, monorepo targets, entrypoints, existing LD usage. First flag Create a boolean first flag, add evaluation, toggle on/off for end-to-end proof. Flag and release change Drive a pull request's change end to end: decide it's flag-worthy, create the guarding flag, wire the new code path behind it on the PR branch, and record an automated release so the change ships safely when the PR merges. Flag release Record an automated rollout for an existing LaunchDarkly flag that guards a pull request's change, so the change releases safely when the PR merges. investigate Analyzes observability data — logs, traces, errors, sessions, and metrics — to find root cause and actionable evidence. Launchdarkly experiment setup Set up and run experiments in LaunchDarkly. Launchdarkly flag cleanup Safely remove a feature flag from code while preserving production behavior. Launchdarkly flag command Resolve `/flag` style requests into the right LaunchDarkly flag lookup flow. Launchdarkly flag create Create and configure LaunchDarkly feature flags in a way that fits the existing codebase. Launchdarkly flag discovery Audit your LaunchDarkly feature flags to understand the landscape, find stale or launched flags, and assess removal readiness. Launchdarkly flag drift Detect and reconcile drift between a feature flag's in-code SDK fallback default and its LaunchDarkly default rule (fallthrough). Launchdarkly flag qualitative feedback setup Integrate LaunchDarkly qualitative user feedback into a JavaScript/TypeScript codebase. Launchdarkly flag targeting Control LaunchDarkly feature flag targeting including toggling flags on/off, percentage rollouts, targeting rules, individual targets, and copying flag configurations between environments. Launchdarkly guarded rollout Configure guarded rollouts with progressive traffic increases, metric monitoring, and automatic rollback. Launchdarkly metric choose Choose the right metrics for a LaunchDarkly experiment, guarded rollout, or release policy. Launchdarkly metric create Create a LaunchDarkly metric that measures what matters for an experiment or rollout. Launchdarkly metric instrument Instrument a LaunchDarkly metric event in a codebase by adding a track() call. Mcp configure Configure the LaunchDarkly hosted MCP server during onboarding. 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. onboarding Onboard a project to LaunchDarkly: kickoff roadmap, resumable log, explore repo, MCP, companion flag skills, nested SDK install (detect/plan/apply), first flag. Online evals Attach judges to config variations for automatic LLM-as-a-judge evaluation. plan Generate a minimal LaunchDarkly SDK integration plan from detected stack: choose SDK type(s), dual-SDK server+client when required, files to change, env conventions. projects Guide for setting up LaunchDarkly projects in your codebase. Sdk install Install and initialize the correct LaunchDarkly SDK during onboarding by running nested skills in order: detect, plan, apply. Should flag change Decide whether a given code change should be placed behind a LaunchDarkly feature flag. snippets Create and manage prompt snippets — reusable text blocks referenced inside config variation prompts. tools Give your agents capabilities through tools (function calling). 
Railway#162
Datadog#35
Sentry#39
Cloudflare Developer Platform#45