Connect your AI Agents to Statsig in minutes

What is a Statsig MCP?

It's an MCP server that lets your agents access data and functionality from Statsig via tools. Your agents can invoke these tools to check a feature gate's rollout status, create or update an experiment, pull event metrics, and review a dynamic config.

Statsig offers an official MCP server, but you can also use one from a third-party platform, like Merge Agent Handler.

How can I use the Statsig MCP server?

The use cases naturally depend on the agent you've built, but here are a few common ones:

• Feature gate rollout monitoring: an agent checks a gate's rollout percentage on a schedule and posts to Slack when it crosses a defined threshold, so the team doesn't have to babysit a gradual rollout manually

• Experiment result summaries: when an experiment reaches statistical significance, an agent pulls the results and writes a summary of the winning variant and lift into a shared doc for stakeholders

• Gradual rollout automation: an agent increases a feature gate's rollout percentage in fixed increments on a set schedule, pausing automatically if error rates spike

• Incident-triggered rollback: when a monitoring tool fires an incident alert tied to a recent release, an agent disables the associated feature gate immediately and notifies the on-call engineer

What are popular tools for Statsig's MCP server?

Here are some of the most commonly used tools:

• list_feature_gates: returns every feature gate in a project along with its current rollout status. Useful for agents that need to audit which gates are live before making rollout changes

• get_feature_gate: returns the configuration and targeting rules for a single feature gate. Use this when an agent needs to check a specific gate's rollout percentage or targeting conditions before acting on it

• update_feature_gate: changes a feature gate's rollout percentage, targeting rules, or enabled status. Call this when an agent is automating a gradual rollout or rolling back a flag during an incident

• list_experiments: returns active and completed experiments in a project. Good for workflows that need to check which experiments are running before summarizing results

• get_experiment_results: returns the metrics, variants, and statistical significance for a given experiment. Helpful when an agent needs to summarize a test's outcome for stakeholders

• list_dynamic_configs: returns the dynamic configs in a project along with their current values. Useful for agents that need to check a config's current state before recommending or making a change

What makes Merge Agent Handler's Statsig MCP server better than alternative Statsig MCP servers?

A few things set it apart from a self-hosted or DIY Statsig MCP setup:

• Enterprise-grade security and DLP: Merge Agent Handler includes built-in data loss prevention controls that let you block or redact sensitive fields before they reach an agent. For Statsig, this means you can prevent experiment result data, targeting rules tied to specific user segments, or API secret keys from being exposed even when the agent has broad read access

• Managed authentication and credentials: Merge stores and refreshes Statsig credentials on your behalf. You never expose raw API keys or OAuth tokens to an agent or manage token rotation manually

• Real-time observability and audit trail: Every tool call made against Statsig is logged with timestamp, tool name, input parameters, and response metadata. You can audit exactly what an agent read or wrote without instrumenting anything yourself

• Tool Packs and controlled access: Tool Packs let you bundle specific Statsig tools with tools from other connectors into a single MCP endpoint, scoped to a specific use case. An agent gets exactly the tools it needs, nothing more

How can I start using Merge Agent Handler's Statsig MCP server?

You can take the following steps:

1. Create or log into your Merge Agent Handler account.

2. Install the Merge CLI by running pipx install merge-api, then run merge configure to link the CLI to your Merge account and merge login to authenticate your session.

3. Register the Agent Handler MCP server with Claude Code by running claude mcp add --transport http agent-handler https://ah-api.merge.dev/mcp, then open Claude Code and run /mcp to confirm agent-handler appears with a connected status.

4. Select agent-handler from the MCP list. This opens a browser window where you select which integrations to authenticate. Choose Statsig and complete the auth flow. Merge stores and manages the credentials going forward.

5. Open a Claude Code session and start querying Statsig data directly. The first time you use a Statsig tool, a Magic Link may appear to complete connector authentication.

If you want to connect Merge Agent Handler's Statsig MCP with internal or customer-facing agentic products, you can follow the steps in our docs.

Can employees use Merge to connect their AI tools to Statsig?

Yes, Merge for Workforce lets your employees connect Claude, ChatGPT, Microsoft Copilot, Cursor, Codex, and other MCP-compatible AI tools to Statsig without bypassing IT governance.

Instead of setting up direct connections with personal credentials that IT can't monitor or revoke, each employee authenticates through Merge and gets individual credentials tied to their identity. A product manager can ask their AI to check a feature gate's rollout percentage, pull an experiment's results, or review which users are in a target audience, all within IT-defined permissions.

IT also provisions access by role or group via SCIM. A product manager, for example, might get Statsig access to check feature gate rollout status, Amplitude access to pull usage trends, and Notion access to document experiment findings, while a growth engineer gets Statsig access to create and update experiments, GitHub access to review flag implementation code, and Slack access to post rollout updates.

Every tool call an employee's AI makes to Statsig is also inspected against your DLP rules and logged to a searchable audit trail, giving security teams full visibility into what data was accessed and by whom.