GrowthBook MCP ThinSAFE
Official GrowthBook MCP server for creating flags, getting experiments, and more.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A thin MCP server for GrowthBook with four tools:
Competence lives in the skills repo and is bundled at build time. Capability is split into read vs write API tools (no per-endpoint formatters) so clients can honor readOnlyHint / destructiveHint correctly.
Tools are prefixed with growthbook_ so they stay unambiguous when a client has multiple MCP servers loaded.
Cursor plugin
Install GrowthBook from the Cursor Marketplace. The plugin connects Cursor to the hosted server at https://mcp.growthbook.io/mcp; the first tool call opens a GrowthBook sign-in to authorize it. Self-hosted GrowthBook users should configure the server manually as described below.
The plugin is defined by .cursor-plugin/plugin.json and mcp.json. To test changes locally, copy the repo into ~/.cursor/plugins/local/growthbook and run Developer: Reload Window.
Install / run
npm install npm run build
Point your MCP client at the compiled entrypoint:
{
"mcpServers": {
"growthbook": {
"command": "node",
"args": ["/absolute/path/to/growthbook-mcp/server/index.js"],
"env": {
"GB_API_KEY": "your_api_key_or_pat",
"GB_API_URL": "https://api.growthbook.io"
}
}
}
}Or run the published package:
npx @growthbook/mcp
Environment variables
62d77c3d9c10OBSERVED · 2026-10-12Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp -- npx -y @growthbook/[email protected]
Exposed tools (5)
3 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
flag-create | write | Create a feature flag |
growthbook_api_read | read | |
growthbook_api_write | write | |
growthbook_list_skills | read | |
growthbook_read_skill | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (5)
.mcpbignore
- `http://127.0.0.1:3333/mcp` — full (skills + API read/write)
- `http://127.0.0.1:3333/mcp/api` — capability-only (`growthbook_api_read` + `growthbook_api_write`)
"url": "http://127.0.0.1:3333/mcp/api"
@modelcontextprotocol/sdk, express, zod, @types/express, @types/node, typescript, vitest
Gates applied: no_behavioural_pass.
62d77c3d9c10full audit observations/trust-audit/mcp-server/growthbook__growthbook-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 62d77c3d9c10 | SAFE | B | 89 | first audit |
Questions
What is the @growthbook/mcp MCP server?
Official GrowthBook MCP server for creating flags, getting experiments, and more.
What tools does @growthbook/mcp expose?
5 in total: 3 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is @growthbook/mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does @growthbook/mcp need?
It reads GB_API_KEY, GB_OAUTH_ISSUER and OPENAI_APPS_CHALLENGE_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does @growthbook/mcp run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as @growthbook/mcp at 2.2.0.
How current is this page?
The grade is for one exact copy of the source (62d77c3d9c10), read on 2026-10-12. The repository is watched and re-audited when it changes.