LaunchDarkly MCP server for AI apps

What your AI apps can do with LaunchDarkly

Create and update flags
Review targeting and rollouts

LaunchDarkly MCP tools

111 tools, taken from the publisher's documentation on 31 October 2026. The server decides what it offers and can add or rename tools at any time; after you connect, Toolstile shows the current list.

Tool	What it does
`vent`	Report a missing capability, bug, parameter gap, or unclear error encountered while using LaunchDarkly MCP tools.
`get-context-instances`	Get all stored instances of a specific context by kind and key.
`search-contexts`	Search for stored LaunchDarkly contexts in an environment by kind, key, or attribute value.
`get-service-connections-usage`	Get a time series of service connection minutes from your LaunchDarkly account.
`match-release-policies`	Resolve which release policies would govern a flag in a given environment; a read-only dry-run of the server-side policy matching logic.
`create-automated-rollout-config`	Record an automated rollout config in LaunchDarkly for a feature-flagged change.
`list-projects`	List LaunchDarkly projects in the account.
`query-change-history`	Query the audit log to find what changed in a LaunchDarkly account.
`update-segment-targets`	Add or remove individual context keys from a segment's included or excluded lists.
`update-segment-rules`	Add, remove, or modify attribute-based targeting rules on a segment.
`get-segment`	Get detailed configuration for a single segment in an environment.
`create-segment`	Create a new segment in a project environment.
`list-segments`	List segments in a project environment.
`delete-prompt-snippet`	Permanently delete a prompt snippet.
`update-prompt-snippet`	Update an existing prompt snippet.
`create-prompt-snippet`	Create a new prompt snippet.
`get-prompt-snippet`	Get a specific prompt snippet by key.
`list-prompt-snippets`	List prompt snippets in a project.
`update-playground`	Update an LLM playground's name, variants, or archived status.
`create-playground`	Create a new LLM playground.
`get-playground`	Get details about a specific LLM playground, including its variants (evaluation definitions and their positions).
`list-playgrounds`	List LLM playgrounds in a project.
`get-evaluation-run-summary`	Get the progress and results of an evaluation run.
`run-evaluation`	Start a run of an AI evaluation.
`create-evaluation`	Create an AI evaluation: a saved prompt, a generation model, and scoring criteria.
`get-evaluation`	Get one AI evaluation by evaluationId (from list-evaluations or create-evaluation).
`list-evaluations`	List AI evaluations in a project with id, version, name, models, messages, criteria, and totalCount.
`delete-dataset`	Permanently delete an offline dataset and its associated metadata.
`create-dataset`	Create an offline dataset for AI evaluation.
`get-dataset`	Get one offline dataset by id with key, name, filename, format, status, rowCount, and createdAt.
`list-datasets`	List offline datasets in a project with id, key, name, filename, format, status (pending, ready, or failed), rowCount, and createdAt.
`stop-guarded-rollout`	Stop an active guarded rollout on a flag's default rule (fallthrough).
`start-guarded-rollout`	Start a guarded rollout on a flag's default rule (fallthrough).
`get-experiment-metric-results`	Get detailed statistical results for a single metric on an experiment iteration.
`get-experiment-results`	Get an overall results summary for an experiment, across every metric on the current iteration.
`stop-experiment-iteration`	Stop the currently running iteration of an experiment.
`save-and-start-experiment-iteration`	Stop the current running iteration, create a new draft iteration with the provided field updates applied, and start it; the API-recommended way to mutate treatments, metrics, methodology, or other fields that are...
`start-experiment-iteration`	Start an experiment iteration.
`update-experiment`	Update fields on an experiment or its current iteration.
`create-experiment`	Create a new experiment on a flag or AgentControl Config.
`get-experiment`	Get detailed information about a specific experiment, including its treatments, metrics, and current iteration status.
`list-experiments`	List experiments in a project, optionally filtered by environment.
`delete-ai-tool`	Permanently delete an AI tool definition.
`update-ai-tool`	Update an AI tool definition's description, schema, tags, or customParameters.
`toggle-agentcontrol-config`	Not supported: always fails with 400.
`get-keys`	Discover available data keys/dimensions for a product type.
`preview-graph`	Preview a chart/graph inline WITHOUT saving it to a dashboard.
`create-graph`	Add a chart/graph to an existing dashboard.
`create-dashboard`	Create a new empty dashboard (visualization) for organizing charts.
`get-dashboard`	Get detailed information about a specific dashboard including all its graphs.
`list-dashboards`	List existing dashboards (visualizations) for the project.
`query-flag-evaluations`	Query flag evaluations for a session.
`query-timeline-events`	Query timeline indicator events for a session.
`query-sessions`	Query project sessions.
`query-error-groups`	Query project error groups.
`query-aggregations`	Retrieve bucketed, aggregated values over time for a product type.
`query-traces`	Query project traces.
`query-logs`	Query project logs.
`get-sdk-active`	Check whether any SDKs have been active in a given environment.
`get-environment`	Get a LaunchDarkly environment's client-side ID and mobile key.
`get-project`	Get a LaunchDarkly project with its environments.
`create-project`	Create a new LaunchDarkly project.
`list-release-policies`	List release policies for a project.
`list-metric-events`	List recent event keys received by a LaunchDarkly project; used to check which events are actively flowing before creating a metric.
`create-metric`	Create a new metric in a LaunchDarkly project.
`get-metric`	Get full details for a single LaunchDarkly metric: measureType, eventKey, successCriteria, unit, description, tags, creation date, and attached flag count.
`list-metrics`	List metrics in a LaunchDarkly project.
`delete-agent-graph`	Permanently delete an agent graph and all of its edges.
`update-agent-graph`	Update an agent graph's metadata or structure.
`create-agent-graph`	Create a new agent graph in a project.
`get-agent-graph`	Get a specific agent graph by key, including its full edge structure.
`list-agent-graphs`	List all agent graphs in a project.
`invite-members`	Invite one or more people to the LaunchDarkly account by email.
`find-members`	Search for LaunchDarkly account members and return their IDs.
`get-member-self`	Return the member ID, profile, and team memberships for the currently authenticated user.
`create-ai-tool`	Create a new AI tool definition in a project.
`get-ai-tool`	Get a single AI tool definition including its full schema, version, tags, and customParameters.
`list-ai-tools`	List AI tool definitions in a project.
`update-agentcontrol-config-rollout`	Set the default (fallthrough) rule for an AgentControl Config in one environment.
`get-agentcontrol-config-targeting`	Read the targeting configuration for an AgentControl Config in a specific environment.
`clone-agentcontrol-config-variation`	Copy an existing variation.
`delete-agentcontrol-config-variation`	Permanently delete an AgentControl Config variation.
`update-agentcontrol-config-variation`	Requires projectKey, configKey, variationKey, and a change.
`create-agentcontrol-config-variation`	Create a variation in an existing config from create-agentcontrol-config.
`get-agentcontrol-config-health`	Health check for an AgentControl Config.
`setup-agentcontrol-config`	Create an AgentControl Config and its first variation in one step, then verify it.
`delete-agentcontrol-config`	Permanently delete an AgentControl Config.
`update-agentcontrol-config`	Update an AgentControl Config's name, description, tags, default variation, judge metric, judge success direction (isInverted), or maintainer.
`create-agentcontrol-config`	Create an AgentControl Config shell in a project.
`get-agentcontrol-config`	Requires projectKey, configKey.
`list-agentcontrol-configs`	Search AgentControl Configs in a project.
`apply-approval-request`	Apply an already-approved flag or segment approval request.
`list-approval-requests`	List approval requests for a flag or a segment in an environment.
`create-approval-request`	Create an approval request for a flag or segment change in an environment that requires approvals.
`check-removal-readiness`	Detailed safety check before removing a feature flag.
`manage-expiring-targets`	List, add, update, or remove expiring targets on a flag.
`delete-flag`	Permanently delete a feature flag.
`archive-flag`	Archive a feature flag (reversible).
`copy-flag-config`	Copy a flag's targeting configuration from one environment to another.
`update-prerequisites`	Add or remove prerequisites for a flag in a specific environment.
`update-individual-targets`	Add or remove specific users or contexts from individual flag targeting.
`update-targeting-rules`	Add, remove, or modify custom targeting rules for a flag in an environment.
`update-rollout`	Change the default rule (fallthrough) for a flag.
`toggle-flag`	Turn a feature flag's targeting on or off in a specific environment.
`update-flag-settings`	Update a flag's top-level settings: name, description, tags, temporary/permanent status, maintainer, default variations, or custom properties.
`create-flag`	Create a new feature flag in a project.
`get-flag-status-across-envs`	Check a flag's lifecycle status across all environments.
`find-stale-flags`	Find feature flags that are candidates for cleanup.
`get-flag-health`	Get combined health view for a single flag: lifecycle state, last-requested timestamp, targeting summary (rules count, targets count, on/off), age, and whether it's temporary.
`get-flag`	Get detailed configuration for a single feature flag scoped to a specific environment.
`list-flags`	Search and browse feature flags in a project.

Suggested access for each AI app

The documentation this list comes from doesn't mark LaunchDarkly's tools as read-only or destructive. Read each tool's description and decide per app before allowing it.

Coding agent in Claude Code or Cursor. Allow the read tools so the agent can look things up without stopping, and require approval for tools that change shared data.

Chat or research app in Claude Desktop. Allow reading and searching. Allow writes only where you want the app to act for you.

Unattended agent, such as a scheduled Codex job. No one is watching the session, so keep it narrow: allow what the job needs, require approval for changes and block the rest.

Blocked tools are removed from the tool list an app sees, so it won't try them. Because rules apply per app, the same LaunchDarkly connection can be broad in one app and read-only in another, and the credential stays in Toolstile instead of each app's config file.

How it works with Toolstile

Connect once. Add LaunchDarkly to a workspace (browser sign-in). Toolstile keeps the credential, so no agent config holds it.
Choose access per app. Give Claude Code every LaunchDarkly tool, give Cursor only the read tools, or keep LaunchDarkly away from an app entirely.
Share approved accounts. Teammates use the connection without copying tokens, and you can remove access in one place.
Review activity. See which app called which tool and when, so you can tighten access with evidence.

Add the LaunchDarkly MCP server to an AI app

Through Toolstile, every AI app uses one gateway entry, whichever servers you connect. In Claude Code:

Shell

claude mcp add --transport http toolstile 'https://mcp.toolstile.com/mcp'

Then connect LaunchDarkly in your workspace and choose which of its tools that app may use. Client setup covers Codex, Cursor and Claude Desktop.

To connect directly instead, add the LaunchDarkly endpoint to each app separately. In Claude Code:

Shell

claude mcp add --transport http launchdarkly 'https://mcp.launchdarkly.com/mcp/fm'

In Cursor's mcp.json:

JSON

{
  "mcpServers": {
    "launchdarkly": {
      "url": "https://mcp.launchdarkly.com/mcp/fm"
    }
  }
}

Some servers accept only clients they have approved, or need a token header. Check the LaunchDarkly MCP documentation for what your client needs.

Before you connect

A LaunchDarkly account. Sign-in uses your LaunchDarkly permissions.

Server details

Detail	Value
Publisher	LaunchDarkly
Endpoint	`https://mcp.launchdarkly.com/mcp/fm`
Authentication	Browser sign-in
Categories	Development
Tool list	111 tools, observed 31 October 2026 (docs)

LaunchDarkly MCP documentation

LaunchDarkly MCP server for Claude, Codex and Cursor