# ConfigCat — how to use (mcp.ai)

Connect your ConfigCat account and use 10 tools for developer tools straight from your AI agent. Connect with your own API key. ConfigCat is a feature flag management service for controlling feature rollouts, configurations, environments, and team access.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_configcat?ms=1787295840000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `configcat_create_setting`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/configcat`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/configcat/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/configcat/create/setting` — Create a feature flag or typed setting in a Config. The key must be unique within that Config.
  - body: { key: string, hint?: string, name: string, order?: integer, is_json?: boolean, tag_ids?: integer[], config_id: string, setting_type: string, initial_values?: object[], predefined_variations?: object[], setting_id_to_init_from?: integer }
- `POST https://api.mcp.ai/api/configcat/delete/setting` — Permanently delete one ConfigCat feature flag or setting by ID. This cannot be undone; verify the setting ID before calling.
  - body: { setting_id: integer }
- `POST https://api.mcp.ai/api/configcat/get/product/context` — Return a ConfigCat Product's configs, environments, segments, and tags, including the identifiers and evaluation versions needed to manage flags and targeting.
  - body: { product_id: string }
- `POST https://api.mcp.ai/api/configcat/get/setting/value/v2` — Get one Config V2 flag or setting's complete evaluation formula in an Environment, including its optimistic-concurrency version.
  - body: { setting_id: integer, environment_id: string }
- `POST https://api.mcp.ai/api/configcat/list/account/hierarchy` — List accessible ConfigCat organizations and products so an agent can resolve the IDs needed by product-scoped tools.
- `POST https://api.mcp.ai/api/configcat/list/environment/values/v2` — Return every Config V2 feature flag and setting evaluation formula for one Config and Environment, preserving ordered targeting rules and concurrency versions while omitting parent objects and updater
  - body: { config_id: string, environment_id: string }
- `POST https://api.mcp.ai/api/configcat/list/settings` — List feature flags and settings in one Config, including IDs, keys, types, tags, and metadata needed by value operations.
  - body: { config_id: string }
- `POST https://api.mcp.ai/api/configcat/patch/setting/value/v2` — Update selected typed fields of one Config V2 evaluation formula while preserving every field the caller omits.
  - body: { reason?: string, setting_id: integer, default_value?: object, environment_id: string, bypass_approval?: boolean, targeting_rules?: object[], latest_version_id: string, percentage_evaluation_attribute?: string, reset_percentage_evaluation_attribute?: boolean }
- `POST https://api.mcp.ai/api/configcat/replace/setting/value/v2` — Completely replace one Config V2 flag or setting evaluation formula in an Environment. Supply the complete default value, ordered targeting rules, and percentage attribute; omitted state is intentiona
  - body: { reason?: string, setting_id: integer, default_value: object, environment_id: string, bypass_approval?: boolean, targeting_rules?: object[], latest_version_id: string, percentage_evaluation_attribute?: string, use_identifier_for_percentage_evaluation?: boolean }
- `POST https://api.mcp.ai/api/configcat/update/setting/metadata` — Partially update a flag or setting's name, hint, or complete tag assignment without resetting untouched metadata.
  - body: { hint?: string, name?: string, tag_ids?: integer[], clear_hint?: boolean, setting_id: integer }

## Example prompts
- "What can I do in ConfigCat?"
- "Show me a summary of my ConfigCat account"

## More
- Page: https://mcp.ai/configcat
- Agent spec (llms.txt): https://mcp.ai/configcat/llms.txt
- Postman collection: https://mcp.ai/configcat/postman.json