ConfigCat MCP Server
Expose ConfigCat feature flag management and SDK integration through the Model Context Protocol.
Key Features
Use Cases
README
ConfigCat MCP Server
The ConfigCat's Model Context Protocol (MCP) server provides access to ConfigCat's public management API for feature flag and configuration management. It also enables your code editor to understand your feature flags, integrate the appropriate ConfigCat SDK into your project or even create new feature flags directly in your codebase.
Features
- Tools:
- Complete set of tools for ConfigCat's public management API operations. You can Create, Read, Update and Delete any entities like Feature Flags, Configs, Environments or Products within ConfigCat.
- Get comprehensive SDK documentation and code examples for seamless feature flag implementation in your project.
Setup
You can use the following environment variables to configure the MCP server.
| Environment variable | Required | Default | Description |
|---|---|---|---|
| CONFIGCAT_API_USER | ☑ | ConfigCat Management API basic authentication username. | |
| CONFIGCAT_API_PASS | ☑ | ConfigCat Management API basic authentication password. | |
| CONFIGCAT_BASE_URL | https://api.configcat.com | ConfigCat Management API host. |
The instructions below shows how to connect a client to the MCP server.
Cursor
- Open
Preferences->Cursor Settings->MCP & Integrations - Click
Add Custom MCP - Add the following server definition for the ConfigCat MCP server:
{
"mcpServers": {
"ConfigCat": {
"command": "npx",
"args": ["-y", "@configcat/mcp-server"],
"env": {
"CONFIGCAT_API_USER": "YOUR_API_USER",
"CONFIGCAT_API_PASS": "YOUR_API_PASSWORD"
}
}
}
}
- Save the settings.
Visual Studio Code
- Create a
.vscode/mcp.jsonfile in your project root with the following content:
{
"servers": {
"ConfigCat": {
"command": "npx",
"args": ["-y", "@configcat/mcp-server"],
"env": {
"CONFIGCAT_API_USER": "YOUR_API_USER",
"CONFIGCAT_API_PASS": "YOUR_API_PASSWORD"
}
}
}
}
- Save the settings file. The MCP server should now be available in VS Code.
Claude Desktop
- Open Settings → Developer
- Click Edit Config
- Open
claude_desktop_config.json - Add the following server definition for the ConfigCat MCP server:
{
"mcpServers": {
"ConfigCat": {
"command": "npx",
"args": ["-y", "@configcat/mcp-server"],
"env": {
"CONFIGCAT_API_USER": "YOUR_API_USER",
"CONFIGCAT_API_PASS": "YOUR_API_PASSWORD"
}
}
}
}
- Save and restart Claude.
Available Tools
Membership Management
Organizations
list-organizations- List all organizations
Members
list-organization-members- List organization memberslist-pending-invitations- List pending invitationslist-pending-invitations-org- List org pending invitationslist-product-members- List product membersinvite-member- Invite a new memberupdate-member-permissions- Update the permissions of a memberdelete-organization-member- Remove organization memberdelete-product-member- Remove product memberdelete-invitation- Cancel invitation
Permission Groups
list-permission-groups- List permission groupscreate-permission-group- Create a new permission groupget-permission-group- Get permission group detailsupdate-permission-group- Update permission groupdelete-permission-group- Delete permission group
General
Products
list-products- List all productsget-product- Get specific product detailsupdate-product- Update existing productdelete-product- Delete a productget-product-preferences- Get product preferencesupdate-product-preferences- Update product preferencescreate-product- Create a new product
Configs
list-configs- List configs for a productcreate-config- Create a new configget-config- Get specific config detailsupdate-config- Update existing configdelete-config- Delete a config
Environments
list-environments- List environments for a productcreate-environment- Create a new environmentget-environment- Get specific environment detailsupdate-environment- Update existing environmentdelete-environment- Delete an environment
Segments
list-segments- List user segmentscreate-segment- Create a new segmentget-segment- Get specific segment detailsupdate-segment- Update existing segmentdelete-segment- Delete a segment
SDK Keys
get-sdk-keys- Get SDK keys for config/environment
Webhooks
list-webhooks- List webhooksget-webhook- Get webhook detailsreplace-webhook- Replace webhook configurationupdate-webhook- Update existing webhookdelete-webhook- Delete a webhookget-webhook-signing-keys- List webhook signing keyscreate-webhook- Create a new webhook
Integrations
list-integrations- List integrationscreate-integration- Create a new integrationget-integration- Get integration detailsupdate-integration- Update existing integrationdelete-integration- Delete an integration
Code References
get-code-references- Get code references
Diagnostics
Audit logs
list-auditlogs- Get product audit logslist-organization-auditlogs- Get organization audit logs
Zombie (stale) flags
list-staleflags- Get stale feature flags report
Feature Flag metadata
Feature Flags & Settings
list-settings- List feature flags for a configcreate-setting- Create a new feature flagget-setting- Get specific feature flag detailsreplace-setting- Replace feature flag configurationupdate-setting- Update existing feature flagdelete-setting- Delete a feature flag
Tags
list-tags- List tags for a productcreate-tag- Create a new taglist-settings-by-tag- Get feature flags by tagget-tag- Get specific tag detailsupdate-tag- Update existing tagdelete-tag- Delete a tag
Feature Flag & Setting Values (v1 & v2 APIs)
get-setting-value- Get feature flag valueupdate-setting-value- Update feature flag valuereplace-setting-value- Replace feature flag valueget-setting-values- Get multiple setting valuespost-setting-values- Update multiple setting values- V2 variants:
*-v2versions of above tools for Config V2
SDK documentation
update-sdk-documentation- Get comprehensive SDK documentation and code examples for seamless feature flag implementation in your project.
API Rate Limits
The ConfigCat public API has rate limits. The server will respect these limits and return appropriate error messages if limits are exceeded.
Security Note
This server is designed for management operations only. Do not use it for evaluating feature flag values in production applications - use the ConfigCat SDKs or ConfigCat Proxy instead.
Need help?
Contributing
Contributions are welcome. For more info please read the Contribution Guideline.
About ConfigCat
Star History
Repository Owner
Organization
Repository Details
Programming Languages
Tags
Topics
Join Our Newsletter
Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.
Related MCPs
Discover similar Model Context Protocol servers
Flipt MCP Server
MCP server for Flipt, enabling AI assistants to manage and evaluate feature flags.
Flipt MCP Server is an implementation of the Model Context Protocol (MCP) that provides AI assistants with the ability to interact with Flipt feature flags. It enables listing, creating, updating, and deleting various flag-related entities, as well as flag evaluation and management. The server supports multiple transports, is configurable via environment variables, and can be deployed via npm or Docker. Designed for seamless integration with MCP-compatible AI clients.
- ⭐ 2
- MCP
- flipt-io/mcp-server-flipt
Firefly MCP Server
Seamless resource discovery and codification for Cloud and SaaS with Model Context Protocol integration.
Firefly MCP Server is a TypeScript-based server implementing the Model Context Protocol to enable integration with the Firefly platform for discovering and managing resources across Cloud and SaaS accounts. It supports secure authentication, resource codification into infrastructure as code, and easy integration with tools such as Claude and Cursor. The server can be configured via environment variables or command line and communicates using standardized MCP interfaces. Its features facilitate automation and codification workflows for cloud resource management.
- ⭐ 15
- MCP
- gofireflyio/firefly-mcp
Insforge MCP Server
A Model Context Protocol server for seamless integration with Insforge and compatible AI clients.
Insforge MCP Server implements the Model Context Protocol (MCP), enabling smooth integration with various AI tools and clients. It allows users to configure and manage connections to the Insforge platform, providing automated and manual installation methods. The server supports multiple AI clients such as Claude Code, Cursor, Windsurf, Cline, Roo Code, and Trae via standardized context management. Documentation and configuration guidelines are available for further customization and usage.
- ⭐ 3
- MCP
- InsForge/insforge-mcp
PostHog MCP
Easily deploy and manage Model Context Protocol servers across multiple platforms.
PostHog MCP provides a server implementation for the Model Context Protocol, now maintained within the PostHog monorepo. It enables quick deployment for enhanced model context management across editors like Cursor, Claude, Claude Code, VS Code, and Zed. Users can install the MCP server with a single command, streamlining integration for large language model workflows. Documentation and further details are provided through official PostHog resources.
- ⭐ 138
- MCP
- PostHog/mcp
Keycloak MCP Server
MCP server for streamlined Keycloak administration and user management
Keycloak MCP Server provides a Model Context Protocol (MCP) interface for managing Keycloak users and realms. It enables easy creation, deletion, and listing of users and realms through standardized tools. Designed for integration with platforms like Claude Desktop and tools like Smithery, it automates repeated Keycloak admin tasks and supports both NPM and local development setups.
- ⭐ 33
- MCP
- ChristophEnglisch/keycloak-model-context-protocol
Vectorize MCP Server
MCP server for advanced vector retrieval and text extraction with Vectorize integration.
Vectorize MCP Server is an implementation of the Model Context Protocol (MCP) that integrates with the Vectorize platform to enable advanced vector retrieval and text extraction. It supports seamless installation and integration within development environments such as VS Code. The server is configurable through environment variables or JSON configuration files and is suitable for use in collaborative and individual workflows requiring vector-based context management for models.
- ⭐ 97
- MCP
- vectorize-io/vectorize-mcp-server
Didn't find tool you were looking for?