ConfigCat MCP server
ConfigCat in any MCP client, through Memtro: ConfigCat does not publish this server. Memtro's ConfigCat connector reads ConfigCat through its API with the credentials you connect, and one endpoint hands those tools, every other system you connect and Memtro's memory tools to Claude Code, Cursor, Claude Desktop or anything else that speaks Streamable HTTP, as you.
What the model can do
ConfigCat feature flags: read products, configs, environments, flags, what each boolean or number flag serves in an environment and the audit log, and turn flags on or off, create, rename, tag and delete flags, and open, approve, apply, close and comment on change requests.
Reads
configcat_list_productsConfigCat products (the top level that holds configs and environments) with their ids.configcat_list_configsThe configs (flag files) in a ConfigCat product, with their ids.configcat_list_environmentsThe environments (Production, Test…) of a ConfigCat product, with their ids.configcat_list_settingsThe feature flags and settings defined in a ConfigCat config: key, name, type (boolean, string, int, double), hint, tags and when created.configcat_flag_valuesWhat each flag in a ConfigCat config serves in one environment: the default value of boolean and number flags…configcat_audit_logConfigCat's audit log for a product: who changed which flag, setting, config or environment, when, and the reason given.configcat_list_tagsThe tags of a ConfigCat product with their ids, for tagging a flag.configcat_list_change_requestsChange requests in a ConfigCat product (proposed flag changes awaiting approval), newest pages first as ConfigCat returns them, with ids, status…
Acts, when you ask
These change something in ConfigCat. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.
configcat_update_flag_valueChanges what a ConfigCat flag serves in one environment: its default value…configcat_create_flagCreates a feature flag (boolean) or setting (string, int, double) in a ConfigCat config.configcat_update_flag_detailsRenames a ConfigCat flag, changes its hint, or adds existing tags to it (not its key or values).configcat_delete_flagPermanently deletes a ConfigCat flag or setting from its config and every environment.configcat_create_change_requestOpens a ConfigCat change request in one environment proposing a new served value for one flag (its default and/or one targeting rule's value)…configcat_approve_change_requestAdds this user's approval to a ConfigCat change request.configcat_apply_change_requestApplies a ConfigCat change request: its proposed flag changes are published immediately to live apps in that environment.configcat_close_change_requestCloses a ConfigCat change request without applying it.configcat_comment_change_requestAdds a comment to a ConfigCat change request, visible to everyone on the product who can see it.configcat_create_tagCreates a tag in a ConfigCat product, for grouping flags.configcat_create_configCreates an empty config (flag file) in a ConfigCat product.configcat_create_environmentCreates an environment (such as Staging) in a ConfigCat product; every flag gets a value there.
Connect it
First connect ConfigCat on Dashboard → Connections, then add Memtro to your client once. The ConfigCat tools appear alongside the tools of everything else you have connected; nothing is configured per connector.
Claude Code
The Memtro plugin registers the server and a skill for when to use it; the tools are then available in every session.
claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...Cursor
Add the server to .cursor/mcp.json in the project, or to the global file under ~/.cursor/.
{
"mcpServers": {
"memtro": {
"url": "https://platform.memtro.com/api/mcp",
"headers": {
"Authorization": "Bearer sk-memtro-..."
}
}
}
}Claude Desktop
Create a personal API key on Dashboard → Profile → API keys. In Claude Desktop add an MCP server of type HTTP with URL https://platform.memtro.com/api/mcp and the header Authorization: Bearer sk-memtro-…
OpenCode
A remote server in opencode.json.
{
"mcp": {
"memtro": {
"type": "remote",
"url": "https://platform.memtro.com/api/mcp",
"headers": {
"Authorization": "Bearer sk-memtro-..."
}
}
}
}Pi
One command: pi mcp add memtro --url https://platform.memtro.com/api/mcp --bearer-token-env-var MEMTRO_API_KEY. Tools arrive as mcp__memtro__*. The pi-memtro extension registers it for you, alongside Memtro as the model.
Any other client
Add an MCP server of type HTTP (Streamable HTTP, stateless) at https://platform.memtro.com/api/mcp with the header Authorization: Bearer sk-memtro-.... Codex, Zed, Windsurf, Cline and the SDKs all take a remote server this way.
Who may use it
The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared ConfigCat connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.
Ask it like this
- › Is newCheckout on in production?
- › Who changed the pricing flag this week?
- › Which flags in the web config are tagged beta?
- › How many targeting rules does darkMode have in Test?
- › Turn darkMode on in Test
Questions
- Is this an official ConfigCat MCP server?
- No. It is Memtro's MCP server with Memtro's ConfigCat connector behind it: the connector reads ConfigCat through its API with the credentials you connect on Dashboard → Connections, and ConfigCat publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.
- What does it cost?
- Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.
- Can it change anything in ConfigCat?
- Only when you ask, and only what it has been granted: turn a flag on or off, or change its default or one targeting rule's served value, in one environment; create a feature flag or setting in a config; rename a flag, change its hint or add tags to it; delete a flag permanently from every environment; open a change request proposing a flag value in an environment that needs approval; approve a change request; apply a change request, publishing its changes immediately; close a change request without applying it; comment on a change request; create a tag, a config or an environment in a product. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.
- Which clients work?
- Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.