Configcat runs on your own machine — the client starts it, so there is no endpoint to ping. 1 802 installs a week from npm. Last commit 2 Nov 2026.
Enables AI agents to interact with ConfigCat, a feature flag service for teams.
Today is the operative word: we check Configcat every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-server -e 'CONFIGCAT_API_USER=<CONFIGCAT_API_USER>' -e 'CONFIGCAT_API_PASS=<CONFIGCAT_API_PASS>' -- npx -y @configcat/mcp-server
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@configcat/mcp-server"
],
"env": {
"CONFIGCAT_API_PASS": "<CONFIGCAT_API_PASS>",
"CONFIGCAT_API_USER": "<CONFIGCAT_API_USER>"
}
}
}
}
[mcp_servers.mcp-server]
command = "npx"
args = ["-y", "@configcat/mcp-server"]
env = { CONFIGCAT_API_USER = "<CONFIGCAT_API_USER>", CONFIGCAT_API_PASS = "<CONFIGCAT_API_PASS>" }
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@configcat/mcp-server"
],
"env": {
"CONFIGCAT_API_PASS": "<CONFIGCAT_API_PASS>",
"CONFIGCAT_API_USER": "<CONFIGCAT_API_USER>"
}
}
}
}
{
"servers": {
"mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@configcat/mcp-server"
],
"env": {
"CONFIGCAT_API_PASS": "<CONFIGCAT_API_PASS>",
"CONFIGCAT_API_USER": "<CONFIGCAT_API_USER>"
}
}
}
}
Put your own values in place of
<CONFIGCAT_API_USER> (ConfigCat Management API basic authentication username), <CONFIGCAT_API_PASS> (ConfigCat Management API basic authentication password).
The author’s registry entry marks them as required.
Optional settings from the registry entry, left out of the block above:
CONFIGCAT_BASE_URL (Base URL for the ConfigCat API. Defaults to `https://api.configcat.com`).
Tasks, sprints, releases and docs for engineering teams with AI coding agents.
Securely search and manage workspace context files for AI agents and teams.
The project tracker for teams of humans and AI agents — in plain files. MCP server + CLI.
Shared memory for teams and their AI agents: Markdown concepts with typed links in shared bundles.
Project tracker for teams working with AI agents: issues, cycles, docs and shared agent memory.
Send, receive, monitor and reply to email from AI agents with threaded inbox context.
Shared memory for teams that work with AI agents: meetings, email and calendar in one brain.
Disposable email inboxes for AI agents: create, wait for mail, extract verification codes
Answers built from our own checks of this server.