by Statsig
Updated October 20, 2026
MCP100 verdict
Not currently recommended. First-party evidence supports Shortlist admission; this is not a Recommended-tier security certification.
MCP100 Assessment
Editorial verdict
Reviewed October 19, 2026
Task Fit
Mapped
Specialized workflows
Trust
Status warning
Shortlist evidence is sufficient for identity, setup and task value; authenticated runtime tool-schema measurement and exhaustive security certification remain out of scope.
Maintenance
Date unavailable
No dated repository or package update is currently stored.
Popularity
Signals unavailable
No independently comparable adoption metric is currently stored.
Evidence scope
No MCP-specific repository metric is stored
No MCP-specific package metric is stored
Stars observed October 20, 2026 · Downloads observed October 20, 2026
Current Statsig V3 MCP is hosted. No current first-party public repository containing the hosted server implementation or an official MCP-specific distribution repository was verified.
Hosted Statsig V3 MCP has no exact public package distribution verified.
Publisher activity observed October 20, 2026
Current source snapshot
Source relationship: First-party MCP
Reviewed October 19, 2026
Evidence-backed setup
Choose your MCP client. A client connects to the MCP server; the language model is selected inside that client. Only stored, source-backed configurations are shown.
Transport not recorded
Complete client-specific setup, verification and removal are not documented in this reviewed source.
Publisher-documented setup is not the same as MCP100 execution testing. “MCP100 logic checked” means the stored configuration shape was reviewed, not that third-party MCP software was run.
Evidence checked 2026-10-20
Type-appropriate, source-backed setup for this mcp server profile.
{"url":"https://api.statsig.com/v3/mcp"}Capability
Statsig MCP is a first-party MCP for inspect and manage statsig experiments, gates, and configuration from an mcp client. Authentication/setup: OAuth; Console API key alternative supported. V3 exposes write and destructive operation lanes in addition to reads. Updates require confirmation where specified, and project permissions/review policies still apply. OAuth requires Personal Console API Keys to be enabled for the user's role.
Exact machine tool inventory is not published.
Statsig V3 replaces 93 V1 tools with 18 default tools plus discovery.
Not measured yet
Estimated token footprint of the MCP tool schemas exposed to the agent.
https://api.statsig.com/v3/mcp
Reviewed access
Related reviewed MCPs
Explore Tableau sites, workbooks, data sources, metadata, and governed analytics.
Choose this instead if
Choose tableau instead if business-intelligence discovery and analysis using authorized Tableau content.
Explore Tableau sites, workbooks, data sources, metadata, and governed analytics.
Connect compatible AI clients to Salesforce's documented MCP capabilities.
Choose this instead if
Choose Salesforce Hosted MCP instead if connect compatible AI clients to Salesforce's documented MCP capabilities.
Use governed Salesforce data, flows, Apex, actions, and queries from compatible MCP clients.
Connect compatible AI clients to ServiceNow's documented MCP capabilities.
Choose this instead if
Choose ServiceNow MCP Server instead if connect compatible AI clients to ServiceNow's documented MCP capabilities.
Expose administrator-selected ServiceNow tools through an instance-scoped MCP endpoint.
Statsig is listed as First-party MCP in MCP100’s current evidence.
Current official resources:
Original product, capability, tool, and usage documentation from the MCP publisher. Installation sections appear under Install & Agents.
Title: Overview
URL Source: https://docs.statsig.com/integrations/mcp/overview
Markdown Content: DocsProduct DocsWarehouse NativeSDKs & APIsManagement & Integrations
Search docs…⌘ K/Full widthStatsig Console
More
Get Started
Experiments
Feature Management
Feature Flags
Dynamic Config
Segments
Release Pipelines
Smart Gate Early Access
Analytics
Product Analytics
Infra Analytics
Alerts
Web Analytics
AI Experimentation
Other Features
Low-Code Experiments
Session Replay
Statsig + AI
Control Panel Early Access
Data & Metrics
Tutorials
Migration Guides
On this page
For AI agents: a documentation index is available at/llms.txt. Append .md to any page URL for markdown, or send Accept: text/markdown.
The Statsig MCP (Model Context Protocol) server brings the power of Statsig into tools like Codex, Cursor, and Claude Code. With this setup, you can ask questions, explore experiments, and access your Statsig data using AI.
Codex Set up Statsig MCP using Codex Desktop App, CLI, or IDE extension.ChatGPT Connector Talk to your Statsig projects from within ChatGPT.
Cursor Configure Statsig MCP in Cursor IDE.Claude Code Set up Statsig MCP in Claude Code.Manual setup Manual configuration for any MCP-compatible tool.
Tool reference Look up MCP tools, actions, and inputs.Automation examples Call the V3 server from scheduled and CI jobs.
Statsig MCP exposes 18 default tools. Tool visibility depends on your permissions and the server configuration.
| Tool group | What it does |
|---|---|
| Context and search | get_context returns your project, permissions, and review settings. search and fetch find and retrieve Statsig resources. |
| Read tools | gate_read, experiment_read, dynamic_config_read, metric_read, and log_read list and inspect gates, experiments, dynamic configs, metrics, metric sources, audit logs, and Logs Explorer data. Each takes an action. |
| Create tools | gate_create, experiment_create, and dynamic_config_create create new resources. These tools require write access. |
| Update tools | gate_update, experiment_update, and dynamic_config_update replace an existing resource. These tools require write access and a confirmation. |
| Discovery tools | discover_tools finds other operations, including layers, segments, Parameter Stores, Autotunes, holdouts, prompts, tags, dashboards, reviews, and partial updates. api_read, api_write, and api_destructive run the operation you discover. |
Clients that use expanded tool exposure also show typed tools for layers, segments, Parameter Stores, and Autotunes.
Your agent can find and run any operation that Statsig exposes through discovery, without a dedicated tool. For the inputs each tool accepts, go to the tool reference.
api_destructive operations require a confirmation. Review each change before your agent supplies a confirmation.api_destructive covers sensitive updates and review actions, not only deletion.The Statsig MCP server supports both GET and POST requests. Read-only users can connect and use all read tools. Write tools require an API key with write permissions. The Statsig MCP server is especially useful for:
text
Copy
You are an expert, diligent Software engineer with the sole goal of reducing the amount of tech debt in the code base. This code base, making use of best practices, leverages feature gates liberally using Statsig. As gates complete their lifecycle in Statsig, they may end up "stale" which means that they're enabled, but no longer checked. Your job is to find these gates, and refactor the codebase to no longer check the gate (instead, changing the check to a constant value).
You should follow coding best practices:
- You should not simply replace gate calls with "True" or "False" but instead carefully trace the logic through to where it is used and change the behavior that way - adjusting the code in minor ways to make the default behavior what the value is that the gate was returning
- You should always strive to write minimal code - readable but terse, never longer than it needs to be
- You should never write comments or debug statements.
You should use the statsig-local MCP to list feature gates, then look for gates that are marked as stale. You should then grep the codebase for that feature flag name, and do a minimal rewrite of the code to no longer use Statsig, removing the checkGate call or similar. When you use the MCP, list gates with type="STALE" and limit=10. Call gate_read with the get_list_of_gates action and the parameters query_type and query_limit. You should select only one gate to do this with, before stopping. If you cannot find the gate after a grep, try the next one you found using the MCP. Once you successfully remove a gate, return.
Was this helpful?
Copy Markdown
On this page