Skip to main content
mcpSource-backedReview first Safety Privacy

ConfigCat MCP Server for Claude

Manage ConfigCat feature flags from Claude — create, update, and delete flags and targeting rules, manage environments, find and clean up stale flags, and audit change history — with the official ConfigCat MCP server and its 52 tools for the full ConfigCat Management API.

HarnessClaude CodeCodexCursorClaude Desktop
Review first review before installing

Open the source and read safety notes before installing.

Safety notes

  • Tools can create, update, and delete feature flags, targeting rules, environments, and segments — changes affect live feature flag configuration.
  • Use `list-staleflags` before deleting flags to identify zombie flags and avoid breaking active SDKs.

Privacy notes

  • Feature flag configurations, targeting rules, audience segments, SDK keys, and audit log entries from your ConfigCat account are surfaced in Claude's context.
  • `CONFIGCAT_API_USER` and `CONFIGCAT_API_PASS` are Management API credentials — keep them in the MCP config env and never commit them to version control.

Prerequisites

  • A ConfigCat account — log in at app.configcat.com.
  • Management API credentials: My Account → Public API Credentials → + Create new credentials (these are separate from SDK keys).
  • Node.js with `npx` available.
  • An MCP client such as Claude Code or Claude Desktop.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
5 minutes
Difficulty
beginner
Tool listing metadata
Disclosure
ConfigCat is a commercial feature flag service. The MCP server is officially maintained by ConfigCat.
Full copyable content
{
  "mcpServers": {
    "configcat": {
      "command": "npx",
      "args": ["-y", "@configcat/mcp-server"],
      "env": {
        "CONFIGCAT_API_USER": "<your-api-user>",
        "CONFIGCAT_API_PASS": "<your-api-pass>"
      }
    }
  }
}

About this resource

Overview

The ConfigCat MCP Server is the official Model Context Protocol server from ConfigCat, providing 52 tools for the full ConfigCat Management API. It lets Claude manage feature flags, targeting rules, environments, segments, webhooks, and SDK keys in natural language — including a dedicated list-staleflags tool for finding zombie flags stuck at 100% rollout that are ready for cleanup. Licensed under MIT.

Key capabilities

  • Feature flags — create, read, update, delete flags and their targeting rules.
  • Flag values — get and set flag values per environment.
  • Environments — list, create, and update environment configurations.
  • Segments — manage user segment definitions for targeted rollouts.
  • Stale flag detection — identify zombie/unused flags with list-staleflags.
  • Audit logs — retrieve change history at product and organization level.
  • SDK keys — retrieve SDK keys per environment.
  • Webhooks — create webhooks and retrieve signing keys.
  • Organization management — invite members, manage permissions.

Tools (52 total, key selection)

Tool Purpose
list-settings / create-setting / update-setting / delete-setting Feature flag CRUD
get-setting-value / update-setting-value Flag value management
list-environments / create-environment / update-environment Environment lifecycle
list-products / list-configs Product and config navigation
list-segments / create-segment / update-segment User segment management
list-staleflags Find zombie/unused flags at 100% rollout
get-sdk-keys Retrieve SDK keys per environment
list-auditlogs / list-organization-auditlogs Audit trail
list-webhooks / create-webhook Webhook management
update-sdk-documentation Fetch SDK code examples for integration

Credentials

ConfigCat uses Management API credentials (not SDK keys) for the MCP server. Generate them at:

My Account → Public API Credentials → + Create new credentials

These credentials use HTTP Basic auth (CONFIGCAT_API_USER / CONFIGCAT_API_PASS) and grant access to the Management API — distinct from SDK keys used in application code.

How it compares

Server Flag CRUD Stale detection Targeting rules Audit logs Notes
ConfigCat MCP Yes Yes Yes Yes 52 tools, official
LaunchDarkly MCP Yes No Yes Yes 14 tools, official
Unleash MCP Yes No Partial No 11 tools, official
GrowthBook MCP Yes No Partial No Official

ConfigCat's list-staleflags tool for zombie flag detection has no equivalent in other feature flag MCP servers.

Installation

Claude Code

claude mcp add configcat \
  -e CONFIGCAT_API_USER=<your-api-user> \
  -e CONFIGCAT_API_PASS=<your-api-pass> \
  -- npx -y @configcat/mcp-server

Claude Desktop

{
  "mcpServers": {
    "configcat": {
      "command": "npx",
      "args": ["-y", "@configcat/mcp-server"],
      "env": {
        "CONFIGCAT_API_USER": "<your-api-user>",
        "CONFIGCAT_API_PASS": "<your-api-pass>"
      }
    }
  }
}

Requirements

  • A ConfigCat account with Management API credentials.
  • Node.js (for npx).
  • An MCP client (Claude Code or Claude Desktop).

Security

  • Management API credentials (API_USER/API_PASS) grant full account access — keep them in the MCP config env and never commit to version control.
  • SDK keys are separate from Management API credentials; the MCP server does not expose live user traffic data.

Source Verification Notes

Verified on 2026-06-18:

  • Official repository configcat/mcp-server (MIT) on npm as @configcat/mcp-server documents all 52 tools, CONFIGCAT_API_USER/CONFIGCAT_API_PASS management credentials, the default CONFIGCAT_BASE_URL, and the list-staleflags capability.
  • ConfigCat documentation at configcat.com/docs/advanced/mcp-server/ describes the integration setup and credential generation process.
  • Claude Code MCP documentation at code.claude.com/docs/en/mcp describes the stdio connector pattern used above.

Source citations

Add this badge to your README

Show that ConfigCat MCP Server for Claude is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/configcat-mcp-server.svg)](https://heyclau.de/entry/mcp/configcat-mcp-server)

How it compares

ConfigCat MCP Server for Claude side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

FieldConfigCat MCP Server for Claude

Manage ConfigCat feature flags from Claude — create, update, and delete flags and targeting rules, manage environments, find and clean up stale flags, and audit change history — with the official ConfigCat MCP server and its 52 tools for the full ConfigCat Management API.

Open dossier
LaunchDarkly MCP Server for Claude

Manage LaunchDarkly feature flags, AI configs, environments, and audit logs from Claude — with the official LaunchDarkly Model Context Protocol server backed by the LaunchDarkly REST API.

Open dossier
Unleash MCP Server for Claude

Create and manage Unleash feature flags from Claude — evaluate whether a change needs a flag, detect existing flags to prevent duplicates, set rollout strategies, toggle environments, and get cleanup guidance — with the official Unleash MCP server following Unleash best practices.

Open dossier
Backlog MCP Server for Claude

Manage Backlog projects from Claude — create and update issues, comment on tickets, manage wiki pages, review pull requests, and navigate your Nulab Backlog space — with the official Backlog MCP server supporting stdio and HTTP transports.

Open dossier
Trust
Install riskReview firstReview firstReview firstReview first
Notes Safety Privacy Safety Privacy Safety Privacy Safety Privacy
Categorymcpmcpmcpmcp
Sourcesource-backedsource-backedsource-backedsource-backed
AuthorConfigCatLaunchDarklyUnleashNulab
Added2026-06-182026-06-182026-06-182026-06-18
Platforms
Claude CodeCodexCursorClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Source repo
Safety notesTools can create, update, and delete feature flags, targeting rules, environments, and segments — changes affect live feature flag configuration. Use `list-staleflags` before deleting flags to identify zombie flags and avoid breaking active SDKs.Feature flag operations include create, update (patch), and delete — changes affect live targeting rules for all users in the environment. Audit log and code reference reads are non-destructive, but flag patch and delete operations are irreversible and will affect production traffic immediately. Scope the API key to the minimum required permissions (read-only for analysis workflows, write only for flag management workflows).`toggle_flag_environment` enables or disables a feature flag in a production environment — confirm before toggling live flags. `create_flag` writes to your Unleash instance; capabilities are scoped by your PAT's permissions. Remote MCP (`--transport http`) is experimental and must be enabled on your Unleash instance.Tools can create, update, and delete projects, issues, wikis, and pull requests — changes affect your live Backlog space. Use `ENABLE_TOOLSETS` to restrict which tool groups are available if you only need read access.
Privacy notesFeature flag configurations, targeting rules, audience segments, SDK keys, and audit log entries from your ConfigCat account are surfaced in Claude's context. `CONFIGCAT_API_USER` and `CONFIGCAT_API_PASS` are Management API credentials — keep them in the MCP config env and never commit them to version control.Feature flag definitions, targeting rules, user segments, AI config prompts, environment configurations, and audit log entries from your LaunchDarkly project are surfaced in Claude's context. Your API key is passed as a CLI argument — store it in Claude Code's MCP config rather than in shell history; rotate keys from the LaunchDarkly Authorization page.Feature flag names, descriptions, targeting rules, rollout configurations, and project metadata from your Unleash instance are surfaced in Claude's context. Your `UNLEASH_PAT` is a secret — store it as an environment variable and do not commit it to version control.Issue content, comments, wiki pages, pull request details, and user information from your Backlog space are surfaced in Claude's context. Your `BACKLOG_API_KEY` grants account-level Backlog access — keep it in the MCP config env and never commit it to version control.
Prerequisites
  • A ConfigCat account — log in at app.configcat.com.
  • Management API credentials: My Account → Public API Credentials → + Create new credentials (these are separate from SDK keys).
  • Node.js with `npx` available.
  • An MCP client such as Claude Code or Claude Desktop.
  • A LaunchDarkly account and an API key from the LaunchDarkly Authorization page (Settings → Authorization → API Keys).
  • Node.js (v18+) with `npx` available, and an MCP client such as Claude Code or Claude Desktop.
  • An Unleash instance (hosted at unleash.cloud or self-hosted).
  • A personal access token with permission to create feature flags (Settings → API Access → Personal access tokens).
  • Node.js 22+ with `npx` available.
  • An MCP client such as Claude Code or Claude Desktop.
  • A Backlog account on backlog.com or your Backlog.jp/enterprise space.
  • A Backlog API key: Personal Settings → API → Generate API Key.
  • Node.js with `npx` available.
  • An MCP client such as Claude Code or Claude Desktop.
Install
claude mcp add configcat -e CONFIGCAT_API_USER=<your-api-user> -e CONFIGCAT_API_PASS=<your-api-pass> -- npx -y @configcat/mcp-server
claude mcp add launchdarkly -- npx -y --package @launchdarkly/mcp-server -- mcp start --api-key YOUR_API_KEY
claude mcp add unleash -e UNLEASH_BASE_URL=https://your-instance.unleash.cloud -e UNLEASH_PAT=your-pat -- npx -y @unleash/mcp@latest --log-level error
claude mcp add backlog -e BACKLOG_DOMAIN=yourspace.backlog.com -e BACKLOG_API_KEY=<your-api-key> -- npx backlog-mcp-server
Config
{
  "mcpServers": {
    "configcat": {
      "command": "npx",
      "args": ["-y", "@configcat/mcp-server"],
      "env": {
        "CONFIGCAT_API_USER": "<your-api-user>",
        "CONFIGCAT_API_PASS": "<your-api-pass>",
        "CONFIGCAT_BASE_URL": "https://api.configcat.com"
      }
    }
  }
}
{
  "mcpServers": {
    "LaunchDarkly": {
      "command": "npx",
      "args": ["-y", "--package", "@launchdarkly/mcp-server", "--", "mcp", "start", "--api-key", "YOUR_API_KEY"]
    }
  }
}
{
  "mcpServers": {
    "unleash": {
      "command": "npx",
      "args": ["-y", "@unleash/mcp@latest", "--log-level", "error"],
      "env": {
        "UNLEASH_BASE_URL": "https://your-instance.unleash.cloud",
        "UNLEASH_PAT": "your-personal-access-token"
      }
    }
  }
}
{
  "mcpServers": {
    "backlog": {
      "command": "npx",
      "args": ["backlog-mcp-server"],
      "env": {
        "BACKLOG_DOMAIN": "yourspace.backlog.com",
        "BACKLOG_API_KEY": "<your-api-key>",
        "MAX_TOKENS": "50000"
      }
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.