B

LaunchDarkly MCP Server

Official LaunchDarkly MCP server for managing feature flags, AI configs, environments, and code references

Overall Score78/100

Score Breakdown

Server Info

Package
@launchdarkly/mcp-server
Registry
npm
Maintainer
LaunchDarklyVendor
Category
Developer Tools
Tags
feature-flagsrolloutsexperimentation
Last Scanned
7 Apr 2026

Findings

6 issues

Authentication & Identity

MEDIUMHTTP/SSE transport supports per-request credentials

Supports stdio and SSE transports. API key passed via --api-key CLI flag or environment variable. SSE transport uses Express with /sse and /message endpoints. No MCP OAuth implementation. Scopes ('read', 'write') control which tools are registered but this is a server-side configuration, not per-request auth.

Remediation

Implement the MCP OAuth spec so users authenticate directly without platform mediation.

Tool Schema Quality

MEDIUMOnly 0 of 19 schemas have parameter constraints

Most schemas lack maxLength, enum, or pattern constraints on string parameters.

Remediation

Add constraints to string parameters, especially on write operations.

LLM Safety

HIGHTool descriptions contain instructional language

Descriptions include directives that could influence LLM behavior beyond tool selection.

Remediation

Remove instructional language. Descriptions should be purely factual.

Data Exposure

MEDIUM3 list operations lack pagination

List tools (list-feature-flags, list-ai-configs, get-environments) use the underlying LaunchDarkly API pagination but do not expose pagination controls to the LLM. The API may return paginated results internally but the MCP tool returns the full response as-is. No field selection support. Full records are returned in all responses.

Remediation

Add limit/offset or cursor-based pagination.

LOWNo field selection on responses

Responses return full records rather than projected fields.

Remediation

Implement field selection to return only relevant fields.

Maintenance & Trust

MEDIUM15 dependency vulnerabilities (9 high)

npm audit found 9 high severity CVEs.

Remediation

Update vulnerable dependencies.

Tools

19 total
NameDescriptionRisk
get-code-referencesIdentifies which repositories have code references to a given flag, helping agents determine if they're operating on the correct repository and understand the scope of cleanup (single vs multi-repo).read
get-flag-status-across-environmentsReturns lifecycle status (new, active, inactive, launched) based on actual usage patterns, evaluation counts, and configuration stability. This is the key intelligence for removal readiness assessment.read
list-feature-flagsRetrieves all feature flags within a project, including metadata and targeting rules. Enables AI agents to enumerate existing flags for inspection, configuration analysis, or generating flag usage reports across environments.read
create-feature-flagCreates a new feature flag within a project. AI agents can use this operation to define feature toggles for controlled rollouts, experimentation, or gated features, automating the flag setup process.write
get-feature-flagFetches the full configuration for a specific feature flag, including environments, variations, and targeting rules. Useful for agents auditing or managing specific feature toggles in a detailed, contextual manner.read
update-feature-flagUpdates the configuration of an existing feature flag. Enables agents to change targeting rules, modify variations, or adapt rollout strategies dynamically in response to user behavior or experiment results.write
delete-feature-flagRemoves a feature flag from the project. Used by AI agents to clean up deprecated toggles that are no longer in use, improving system hygiene and maintainability.admin
get-environmentsIdentifies which environments exist in a project and determines which are marked as "critical" (production, staging, etc.). Allows agents to programmatically identify critical environments instead of hardcoding assumptions.read
get-ai-config-targetingRetrieves the targeting details of a specific AI Config, including individual targets, rules, and rollouts.read
update-ai-config-targetingUpdates the targeting of an existing AI Config.write
list-ai-configsRetrieves AI configuration settings for a specific project. This endpoint allows agents to access and modify AI-related configurations, ensuring that the AI's behavior aligns with project requirements and user expectations.read
create-ai-configCreates a new AI Config within a project. Useful for setting up LLM configurations programmatically.write
delete-ai-configDeletes an AI Config and its associated variations. Intended for cleanup or deprecation workflows.admin
get-ai-configRetrieves details of a specific AI Config, including variations and model settings.read
update-ai-configUpdates metadata or configuration of an existing AI Config.write
create-ai-config-variationAdds a new variation to an AI Config, supporting experimentation or multi-model strategies.write
delete-ai-config-variationDeletes an AI Config variation.admin
get-ai-config-variationRetrieves an AI configuration variation.read
update-ai-config-variationUpdates a specific variation within an AI Config. Enables fine-tuned control of model behavior.write

Deploy LaunchDarkly MCP Server securely

CompleteFlow adds per-user authentication, permission scoping, and audit logging to any MCP server out of the box.

Deploy on CompleteFlow