Statsig MCP server
Statsig in any MCP client, through Memtro: Statsig does not publish this server. Memtro's Statsig connector reads Statsig 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
Read Statsig feature gates (enabled, rules, who owns them), experiments (status, hypothesis, groups, metrics, decision) and the project's audit log of who changed what. Can create, enable, disable, launch, archive and delete gates, force users to pass or fail a gate, create, start, decide and archive experiments, and create or rename tags when you ask.
Reads
statsig_list_gatesFeature gates in Statsig: name, description, whether enabled, status, type (temporary, permanent, stale), tags, owner…statsig_get_gateOne feature gate in full: its rules with pass percentage, environments and the kind of conditions each targets…statsig_list_experimentsExperiments in Statsig: name, hypothesis, status (setup, active, decision_made, abandoned…), type, start and end, the decision and why…statsig_audit_logThe project's audit log, newest first: what was changed (gate, experiment, config…), the change, the action type, when and by whom.
Acts, when you ask
These change something in Statsig. 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.
statsig_create_tagCreates a tag in the Statsig project (a label with a description that gates, experiments and configs can be filed under).statsig_update_tagRename a Statsig tag or change its description; everything filed under it keeps it.statsig_create_gateCreate a Statsig feature gate with no rules, so it passes nobody until rules are added in the console.statsig_enable_gateEnable a Statsig feature gate, so its rules apply again and the users they match see the feature immediately.statsig_disable_gateDisable a Statsig feature gate, so it fails for everyone and every user loses the feature immediately (a kill switch).statsig_launch_gateLaunch a Statsig feature gate, so it passes for everyone and every user gets the feature immediately.statsig_archive_gateArchive a Statsig feature gate.statsig_delete_gatePermanently delete a Statsig feature gate; code still checking it gets the default (false).statsig_override_gate_usersForce the named user ids to pass or fail a Statsig gate whatever its rules say, effective immediately for those users.statsig_create_experimentCreate a Statsig experiment in setup, with Statsig's default groups unless changed in the console.statsig_start_experimentStart a Statsig experiment: real users are assigned to its groups from now and see the variants.statsig_decide_experimentFinish a Statsig experiment by shipping one group to everyone in it (optionally holding some users back).statsig_archive_experimentArchive a Statsig experiment; it stops being listed as active and can be unarchived in the console.
Connect it
First connect Statsig on Dashboard → Connections, then add Memtro to your client once. The Statsig 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 Statsig 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
- › Who turned the new checkout gate off, and when?
- › Which feature gates are stale?
- › How is the onboarding experiment going, and what are its metrics?
- › What changed in Statsig in the hour before the incident?
- › Disable the new checkout gate now
Questions
- Is this an official Statsig MCP server?
- No. It is Memtro's MCP server with Memtro's Statsig connector behind it: the connector reads Statsig through its API with the credentials you connect on Dashboard → Connections, and Statsig 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 Statsig?
- Only when you ask, and only what it has been granted: create a tag; rename or redescribe a tag; create a feature gate (passes nobody until it has rules); enable a feature gate (users see it at once); disable a feature gate (users lose it at once); launch a feature gate to everyone; archive a feature gate; delete a feature gate (permanent); force named user ids to pass or fail a gate; create an experiment in setup; start an experiment (assigns real users); finish an experiment by shipping one group; archive an experiment. 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.