---
title: "Statsig MCP integration for LuumenAI"
url: "https://www.luumen.ai/integrations/statsig-mcp/"
entity: SoftwareIntegration
category: "AI & automation"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# Statsig MCP integration for LuumenAI

Read gates, experiments, and configs in Statsig, then change them through review

## What LuumenAI can do with Statsig MCP

LuumenAI connects to Statsig MCP with OAuth 2.0 and exposes 93 tools (48 read-only · 22 write · 23 destructive). For connected tools, admins configure which actions may run automatically and which require approval, within the access granted to the user.

## Key facts

- Authentication: OAuth 2.0
- Tools available: 93 tools (48 read-only · 22 write · 23 destructive)
- Deployment: scoped as part of your Pilot, Platform, or Managed rollout
- Category: AI & automation

## About Statsig MCP with LuumenAI

Connect Statsig and Luumen can read your experiments, feature gates, dynamic configs, layers, metrics, segments, and audit logs on demand. Ask what changed on a config last week, or who can approve a pending review. When a change is needed, Luumen opens or approves the review and shows you the exact proposal first.

## Example tools

Read-only (48 in total):

- `STATSIG_MCP_CLUSTER_LOG_PATTERNS` — Cluster similar log lines into templates (same as `statsig-query log-patterns`).
- `STATSIG_MCP_FETCH` — Fetch the full document for a search result id.
- `STATSIG_MCP_GET_AUDIT_LOGS` — List audit logs for this Statsig project.
- `STATSIG_MCP_GET_AUTOTUNE_ELIGIBLE_REVIEWERS` — List the users and reviewer groups eligible to approve/reject a review of this autotune experiment.
- `STATSIG_MCP_GET_AUTOTUNE_REVIEW_BY_ID` — Get a single review for an autotune experiment by its review ID, including its status, proposed change type, author, and requested reviewers.
- `STATSIG_MCP_GET_CONTEXT` — Bootstrap the authenticated Statsig MCP session.
- `STATSIG_MCP_GET_DYNAMIC_CONFIG_DETAILS_BY_ID` — Get the details (including rules, return values, and more) for a Dynamic Config (static, targetable JSON) in the Statsig console.
- `STATSIG_MCP_GET_DYNAMIC_CONFIG_ELIGIBLE_REVIEWERS` — List the users and reviewer groups eligible to approve/reject a review of this dynamic config.

Write and destructive (45 in total, subject to configured approval policy):

- `STATSIG_MCP_APPROVE_AUTOTUNE_REVIEW` — Approve an in-flight review of an autotune experiment.
- `STATSIG_MCP_APPROVE_DYNAMIC_CONFIG_REVIEW` — Approve an in-flight review of a dynamic config.
- `STATSIG_MCP_APPROVE_EXPERIMENT_REVIEW` — Approve an in-flight review of an experiment (A/B test).
- `STATSIG_MCP_APPROVE_GATE_REVIEW` — Approve an in-flight review of a gate (feature flag).
- `STATSIG_MCP_CANCEL_AUTOTUNE_REVIEW` — Cancel (withdraw) an in-flight review of an autotune experiment.
- `STATSIG_MCP_CANCEL_DYNAMIC_CONFIG_REVIEW` — Cancel (withdraw) an in-flight review of a dynamic config.
- `STATSIG_MCP_CANCEL_EXPERIMENT_REVIEW` — Cancel (withdraw) an in-flight review of an experiment (A/B test).
- `STATSIG_MCP_CANCEL_GATE_REVIEW` — Cancel (withdraw) an in-flight review of a gate (feature flag).

## Frequently asked questions

### How does LuumenAI connect to Statsig MCP?

Authorize once with OAuth 2.0. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

### Can LuumenAI change things in Statsig MCP on its own?

For connected tools, admins configure which actions may run automatically and which require approval, within the access granted to the user.

### Is there an audit trail?

Every call to Statsig MCP — read or write, approved or declined — is recorded with the actor, the input, and the result.

Full page: https://www.luumen.ai/integrations/statsig-mcp/