LaunchDarkly MCP

Create a new LLM playground. A playground lets you compare AgentControl Config variations side-by-side. Provide a name and variants : each variant references an evaluation definition (by evaluationId) and a display position.

Get the health status of an AI Config including latency, error rates, and evaluation metrics.

Update an LLM playground's name, variants, or archived status. All fields are optional.

Get the targeting rules and rollout configuration for an AI Config in a specific environment.

Add or remove prerequisites for a flag in a specific environment. Prerequisites are other flags that must evaluate to specific variations before this flag is evaluated. Use addPrerequisite to migrate prerequisites onto a new flag, or removePrerequisite + addPrerequisite to update dependent flags to point to a new key. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.

Get a time series of service connection minutes from your LaunchDarkly account. Use this for capacity planning, cost analysis, and before/after deploy comparisons (e.g. compare daily incremental minutes around a deploy date).

Create a new AI tool definition in a project. The schema should be a raw JSON Schema object with type, properties, and required fields (e.g. {"type": "object", "properties": {...}}). Do NOT use the OpenAI function calling wrapper format. After creation, attach the tool to a variation using update-agentcontrol-config-variation.

Health check for an AgentControl Config. Detects common issues: missing models (NO MODEL in UI), missing prompts, orphaned tool references, and empty configs with no variations. Returns a health verdict (healthy, warning, unhealthy) with specific issues and per-variation summaries. Run before updating or experimenting with a config.

Update an AI tool definition's description or schema. All fields are optional: only provided fields are updated. The schema should be a raw JSON Schema object with type, properties, and required fields.

Read the targeting configuration for an AgentControl Config in a specific environment. Returns variations (with their _id UUIDs and names), individual targets, custom rules, fallthrough (default rule), and off variation. The variation name returned here can be passed as 'variationKey' to update-agentcontrol-config-targeting, update-agentcontrol-config-rollout, and update-agentcontrol-config-targets. Alternatively, use get-agentcontrol-config to obtain the variation's slug key.

Create a new AI Config in a project. An AI Config manages AI model configurations with feature flag-style targeting and experimentation.

Get the on/off status and targeting summary for a feature flag across all environments in a project.

Update the metadata for an AI Config such as name, description, and tags.

Get the status of an AI Config across all environments in a project.

Create a new agent graph in a project. An agent graph defines a directed graph of AgentControl Configs for multi-agent workflows. Provide a rootConfigKey and edges to define the graph structure, or create the graph with just metadata and add edges later via update-agent-graph. If rootConfigKey or edges are provided, both must be present.

Update a feature flag's global settings such as name, description, tags, temporary status, and maintainer.

Create a new reusable prompt snippet.

Add, remove, or modify attribute-based targeting rules on a segment. Rules evaluate context attributes to determine segment membership. Clauses within a rule are ANDed; multiple rules use OR logic. Supported kinds: addRule, removeRule, addClauses, removeClauses, updateClause, addValuesToClause, removeValuesFromClause, reorderRules, updateRuleDescription, updateRuleRolloutAndContextKind. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.

Create an approval request for a flag change in an environment that requires approvals. Provide the same semantic patch instructions you would use for a direct change. The request will be reviewed by approvers before taking effect. Does NOT approve the request: that must be done by a human reviewer.

Update an existing prompt snippet. Creates a new version of the snippet. All fields are optional : only provided fields are updated.

Create a new AgentControl Config in a project. This creates the config shell: use create-agentcontrol-config-variation next to add a model, prompts, and parameters. Mode determines whether variations use 'instructions' (agent), 'messages' (completion), or 'messages' (judge). Judge-mode configs evaluate other AgentControl Config outputs. IMPORTANT: evaluationMetricKey (format: $ld:ai:judge:) is REQUIRED when mode is 'judge'; omitting it will cause a 400 error. For agent and completion mode it is not accepted. Pass viewKeys to link the new config to one or more views at creation time (Views are an Enterprise feature).

Add or remove individual context keys from a segment's included or excluded lists. Included targets always match the segment. Excluded targets never match, even if rules would include them. Supported kinds: addIncludedTargets, removeIncludedTargets, addExcludedTargets, removeExcludedTargets. Each instruction requires contextKind and values. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.

Create a new variation for an AI Config with specific model, prompt, and parameter settings.

Add, remove, or modify custom targeting rules for a flag in an environment. Rules evaluate top-to-bottom; first matching rule wins. Use get-flag to look up rule _ids, clause _ids, and variation _ids before constructing instructions.

Record an automated rollout config in LaunchDarkly for a feature-flagged change.

Add or remove specific users or contexts from individual flag targeting. Individual targets are the highest priority: they override all rules. Supported instruction kinds: addTargets, removeTargets, replaceTargets. To target non-user context kinds (e.g. organization), include contextKind on the instruction (e.g. { kind: 'addTargets', contextKind: 'organization', values: ['org-123'], variationId: '' }). Note: addContextTargets and removeContextTargets are NOT supported by the LD API; use addTargets/removeTargets with contextKind instead. Responses truncate long lists. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.

Create a variation for an AgentControl Config. A variation defines the model, prompts, parameters, and tools. modelConfigKey must be in Provider.model-id format (e.g. OpenAI.gpt-4o, Anthropic.claude-sonnet-4-5) for models to display correctly in the UI. Agent-mode configs use 'instructions' (a string); completion-mode configs use 'messages' (an array of {role, content} objects). To attach AI tools, pass the 'tools' array with {key, version} entries (create tools first with create-ai-tool). To attach judges, pass judgeConfiguration with a judges array of {judgeConfigKey, samplingRate} entries.

Update an AgentControl Config's metadata: name, description, tags, or archive status. Does NOT modify variations: use update-agentcontrol-config-variation for model, prompt, or parameter changes. Set archived: true to archive (reversible).

Report a missing capability, bug, parameter gap, or unclear error encountered while using LaunchDarkly MCP tools. This feedback is collected and triaged to improve the toolset. Use this when a tool is missing, returns an unexpected error, or lacks a needed parameter.

Update the rollout percentages for an AI Config's default rule in a specific environment.

Discover available data keys/dimensions for a product type.

Update a specific variation of an AI Config, including its prompt, model settings, and parameters.

Get details about a specific metric including its configuration and associated experiments.

Update the default (fallthrough) rule for an AgentControl Config in an environment. Set a percentage rollout across variations, or serve a single variation to all unmatched contexts. Weights must sum to 100. Use human-friendly percentages (e.g., 80 for 80%). Accepts a variation key (from get-agentcontrol-config) or variation name (from get-agentcontrol-config-targeting); the tool resolves either to the internal variation _id (UUID) before patching. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-agentcontrol-config-approval` with the returned instructions to submit it for review.

Search and browse feature flags in a project. Returns a paginated list scoped to a single environment.

Update an AgentControl Config variation's name, description, model, instructions/messages, parameters, attached tools, or judge configuration. All fields are optional: only provided fields are updated. Pass 'name' to rename the variation in place without recreating it (avoids changing the variation _id). To attach tools, pass the 'tools' array with {key, version} entries (create tools first with create-ai-tool). Pass an empty tools array to detach all tools. To attach judges, pass judgeConfiguration with a judges array of {judgeConfigKey, samplingRate} entries. Pass an empty judges array to detach all judges.

Query project logs. Retrieve logs for a given project with explicit date range parameters.

Update the targeting rules for an AI Config in a specific environment.

Get details about a specific offline dataset by ID, including its processing status and row count.

Update the individual user targeting for an AI Config in a specific environment.

Get details about a specific LaunchDarkly project, including its environments and settings.

Add a chart/graph to an existing dashboard.

List metrics in a LaunchDarkly project. Returns key, name, measureType (count/occurrence/value), eventKey, successCriteria, tags, and how many flags each metric is attached to.

Query project traces. Retrieve traces for a given project with explicit date range parameters.

Create a new metric in a LaunchDarkly project.

Get detailed information about a specific dashboard including all its graphs.

Check whether any SDKs have been active in a given environment. Returns true if any SDK has initialized or sent events in the environment. Use this to verify that an environment is actually in use before cleanup. Optionally filter by sdkName or sdkWrapperName to check a specific SDK.

List offline datasets for a project. Returns id, name, status, row count, and creation info for each dataset.

Preview a chart/graph inline WITHOUT saving it to a dashboard. Always use this tool first when a user asks to create or visualize a chart. Returns both the graph configuration and the queried metrics data so the user can see the chart rendered inline. After showing the preview, ask the user if they want to save it to a dashboard (using create-graph).

Create a new offline dataset for AI evaluation. Provide a dataset name, filename, and format (csv, json, or jsonl). The dataset is created in pending status and must be uploaded separately. Returns the dataset ID and upload URL.

Create a new LaunchDarkly project. Projects are top-level containers for feature flags and environments.

Get details about a specific evaluation definition, including its configuration and last run status.

Get details about a specific experiment including its configuration, current iteration status, and metric assignments.

Query project sessions. Retrieve sessions for a given project with explicit date range parameters.

Start a new run of an AI evaluation. This executes the evaluation against the configured dataset and judge criteria. Returns the run ID and status.

Get details about a specific environment in a project, including its keys and settings.

List existing dashboards (visualizations) for the project.

Create a new empty dashboard (visualization) for organizing charts.

List AI Config evaluations in a project. Returns evaluation definitions with their names, associated config keys, and last run info.

List experiments in a project, optionally filtered by environment. Returns key, name, description, and current iteration status for each experiment.

Create a new AI evaluation definition. An evaluation defines a comparison between AI Config variations using a dataset and judge criteria. After creation, use run-evaluation to start an evaluation run.

Create a new experiment on a flag or AgentControl Config. An experiment measures the impact of different variations on specified metrics. You must provide the initial iteration definition including a hypothesis, metrics, treatments, and flag configuration. One treatment must be marked as the baseline. Use `methodology` to pick the results-analysis approach (`bayesian` default, `frequentist`, or `export_only` for data-export-only mode). Use `analysisConfig` to set thresholds and multiple-comparison correction. Use `iteration.attributes` to declare slicing dimensions and `iteration.covariateId` to enable stratified sampling.

List recent event keys received by a LaunchDarkly project : used to check which events are actively flowing before creating a metric. Returns up to 50 event keys with last-seen timestamps. If the event key you need isn't here, it may not be instrumented yet.

Query project error groups. Retrieve error groups for a given project with explicit date range parameters.

Update an agent graph's metadata or structure. All fields are optional. If rootConfigKey or edges are provided, both must be present and will fully replace the existing graph structure. Pass name or description to update metadata only.

Update fields on an experiment or its current iteration. Which fields are mutable depends on the current iteration's status (not_started, running, stopped). This tool first reads the experiment's mutableFieldsByStatus, applies only the updates that are allowed for the current status via the updateExperimentFields semantic patch, and returns any rejected fields under `skipped` with the reason. If no provided field is mutable, the response includes `currentStatus` and `allowedFields` so you can retry with valid inputs.

Retrieve bucketed, aggregated values over time for a product type. Returns time-series buckets (not raw events) suitable for charting trends, comparing groups, and computing sums/averages/percentiles. Use this instead of query-logs/query-traces/query-sessions/query-error-groups when you want aggregated values over a window rather than individual records.

Stop an active guarded rollout on a flag's default rule (fallthrough). This immediately halts the progressive rollout and locks the flag to its current state. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.

List release policies for a project. Each policy defines preferred release methods and the metrics or metric groups that automatically attach to guarded rollouts when the policy's conditions match (e.g. specific environments or flag tags).

Query timeline indicator events for a session. Retrieve timeline indicator events for a specific session to understand what happened during that session. Keep in mind that this will not include flag evaluation events, you must use the query-flag-evaluations tool to retrieve those.

Start a guarded rollout on a flag's default rule (fallthrough). A guarded rollout progressively increases traffic to the test variation through a series of stages while monitoring metrics for regressions. Each stage specifies a rolloutWeight (percentage in thousandths, e.g. 10000 = 10%) and a monitoring window in milliseconds. Metrics define what to monitor and whether to notify or rollback on regression. Requires the flag to be on and not already have an active guarded rollout. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.

Get an overall results summary for an experiment, across every metric on the current iteration. Discovers the iteration's metrics, then fetches each metric's analysis from LaunchDarkly's internal results API and returns a compact per-metric summary: which treatment is leading (isBest) : the arm with the highest probability to beat the baseline for Bayesian experiments, or the lowest p-value versus control for frequentist (note: not significance-gated, so a treatment can be flagged leading even when nothing is significant) : each treatment's lift versus control, whether it's statistically significant, and sample sizes. Pass iterationId to summarize a previous iteration. For the full per-treatment statistics (intervals, p-values, Bayesian probabilities) on one metric, use get-experiment-metric-results.

Query flag evaluations for a session. Retrieve flag evaluation events for a specific session to understand which feature flags were evaluated during that session.

Get the summary results of a completed evaluation run, including pass/fail counts and aggregate scores.

Stop the currently running iteration of an experiment. Data collection ends and the iteration moves to the `stopped` status. A winning treatment is required to stop: pass `winningTreatmentId` (the `_id` of one of the iteration's treatments, available from get-experiment) and an optional `winningReason` explaining the call. If the experiment was inconclusive, declare the baseline/control treatment as the winner.

Start an experiment iteration. This begins data collection for the experiment's current draft iteration and starts allocating live end-user traffic across its treatments. The experiment's flag must be toggled on, a randomization unit must be set, and at least one treatment must have a non-zero allocation percent.

Get detailed statistical results for a single metric on an experiment iteration. Returns, per treatment: sample sizes (analyzedUnitCount, trafficCount, conversionCount), the observed mean and standard deviation, and a `statistics` block with the lift versus control (relativeDifferences: estimate plus lower/upper interval bounds and, for frequentist experiments, a per-comparison pValue), the overall pValue, Bayesian probabilities (probabilityToBeBest, probabilityToBeatBaseline, expectedLoss), and an isSignificant flag. Reads from LaunchDarkly's internal analysis API. Defaults to the current iteration and the latest analysis; pass iterationId to target a previous iteration. Use disableMultipleComparisonCorrection / disableSequentialTesting to see uncorrected numbers. Use get-experiment-results for a cross-metric overview, or get-experiment to discover metric keys.

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 locked while an iteration is running. Provide `changeJustification` to record why a new iteration is needed. Field inputs are the same as `update-experiment`; updates are checked against the new iteration's not_started mutability rules. Fields not allowed in not_started are returned under `skipped` rather than being sent.

Turn a feature flag on or off in a specific environment. When off, all users receive the off variation.