Manages Statsig feature gates, experiments, dynamic configs and metrics from Cursor, Claude Code or Codex, so engineers can clean up stale flags and run A/B tests from chat.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your assistant, with Statsig MCP connected:
- Feature Gates
Use Statsig MCP to list feature gates: ‹what you need›
- Experiments
Use Statsig MCP to list A/B experiments: ‹what you need›
- Dynamic Configs
Use Statsig MCP to read dynamic configs: ‹what you need›
Connect it over MCP
{
"mcpServers": {
"statsig-mcp": {
"url": "https://api.statsig.com/v3/mcp"
}
}
}claude mcp add --transport http statsig-mcp https://api.statsig.com/v3/mcp
In Grok, ChatGPT and other assistants, add a custom connector with the address https://api.statsig.com/v3/mcp (how, step by step).
It may ask you to sign in to Statsig or for a key when you add it; the setup guide says which.
Setup guide: docs.statsig.com/integrations/mcp/manual-setup
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- MCP
- Auth
- OAuth 2.0
- Skills
- 5
Skills
Feature Gates
Lists, inspects, creates and updates feature gates with gate_read, gate_create and gate_update, so agents can find and remove stale gates.
Experiments
Lists, inspects, creates and updates A/B experiments with experiment_read, experiment_create and experiment_update, under project review rules.
Dynamic Configs
Reads, creates and replaces dynamic configs with dynamic_config_read, dynamic_config_create and dynamic_config_update, given write access.
Metrics and Logs
Inspects metrics, metric sources, audit logs and Logs Explorer data with metric_read and log_read to summarize console information in the IDE.
Operation Discovery
Finds and runs further operations such as layers, segments, holdouts and dashboards through discover_tools, api_read, api_write and api_destructive.