# Statsig MCP connector

Connect Statsig to Elaichi and Claude, ChatGPT, Cursor or any MCP client can list, inspect, create and update the feature gates, experiments, dynamic configs and metrics each person on your team already has access to.

Source: https://elaichi.ai/connectors/statsig/

## Facts

| | |
| --- | --- |
| Application | Statsig |
| Category | Feature Flag |
| Authentication | Connects over OAuth |
| Bring your own OAuth app | No |
| Native MCP | Yes. Statsig builds and runs this MCP server. Elaichi adds sign-in, access controls and an audit log on top |
| Support for its tools | www.statsig.com/contact |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Statsig is connected

- Which feature gates are fully rolled out in production?
- Summarize the results of the checkout redesign experiment.
- Create a dynamic config for the spring pricing banner.

## Connect Statsig in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Statsig.
2. Optionally set Share with, then press Connect.
3. Approve it in Statsig. Statsig's own window opens. Whoever approves it decides what this connection can reach.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Statsig tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Statsig MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Statsig MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web today. The plugin directory lives at chatgpt.com/plugins.

## Statsig MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Connect Statsig to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Only Read is granted by default, which is not enough to call a Statsig tool. Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone.

## What teams do with Statsig through Elaichi

### Check which gates are on before launch

Product. Ask which feature gates are fully rolled out, which are still partial, and who they target, then read the rules without opening the Statsig console.

### Create a gate without leaving the editor

Engineering. From Cursor, ask for a new feature gate in Statsig named for the feature you are building, with the rollout rule you want, if your Statsig role allows writes.

### Read experiment results in plain language

Growth. Ask how an experiment is performing, which variant is ahead, and whether it has reached significance, with the answer pulled from the live experiment in Statsig.

### Inspect the metrics behind an experiment

Data. List the metrics attached to an experiment in Statsig, check how each one is defined, and spot the ones that are missing before a readout.

### Update a dynamic config for a campaign

Marketing. Change the copy or dates held in a dynamic config in Statsig for a promotion, and confirm what it looked like before and after.

### Explain why a customer sees a feature

Support. Look up the feature gate that controls a feature in Statsig and read its targeting rules to tell a customer why they do or do not see it.

## Elaichi vs Zapier MCP vs Composio for Statsig

All three can connect Statsig to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Statsig tools | Allow or restrict single Statsig tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Statsig call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect Statsig to Claude?

In Elaichi, choose Statsig and sign in with your Statsig account over OAuth. There is no OAuth application to register and no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude can then work with your feature gates, experiments, dynamic configs and metrics.

### Does Statsig work with ChatGPT and Cursor as well as Claude?

Yes. Once Statsig is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You connect Statsig once and every client gets it.

### What can an AI agent actually do with my Statsig data?

An agent can list and inspect your feature gates, experiments, dynamic configs and metrics in Statsig, and explain them in plain language. If your Statsig role allows writes, it can also create or update a gate, an experiment or a dynamic config when you ask. Short concrete asks, such as naming the gate you mean, work better than long sentences.

### Does connecting Statsig give the AI access to my whole project?

No. Access follows the person who signed in to Statsig, so an agent sees only the projects, gates and experiments that person can already see, and can write only where their Statsig role allows. Elaichi can narrow that access further with restrictions, and it never widens it.

### Can my team share one Statsig connection?

Yes. One person connects Statsig in Elaichi and shares the connection with a team, and nobody else ever handles a credential. Each teammate still signs in to Elaichi as themselves, so the audit log names the person behind every call to Statsig.

### Can I stop an agent from deleting or changing things in Statsig?

Yes. In Elaichi, restrictions on the Statsig connection are set per action, so you can allow reading gates and experiments while blocking any create or update. A restricted action is never shown to Claude, ChatGPT or Cursor at all, so no prompt can reach it.

### What happens to a Statsig connection when someone leaves?

Offboarding that person in Elaichi ends their access to Statsig through every client at once. A Statsig connection shared with a team keeps working for everyone else. Disconnecting Statsig once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client together.

### Does the Statsig MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Statsig is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for Statsig?

Yes. Both let Claude, ChatGPT or Cursor use Statsig. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Statsig call.

### How is Elaichi different from Composio for Statsig?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Statsig: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.