Skip to main content
Glama
growthbook

GrowthBook MCP Server

Official
by growthbook
README.md
# GrowthBook MCP Thin

A thin MCP server for GrowthBook with four tools:

| Tool | Purpose |
|------|---------|
| `growthbook_list_skills` | List top-level skill entry points (name + description) |
| `growthbook_read_skill` | Return a listed skill or qualified child workflow (`feature-flags` or `feature-flags/references/flag-create`) |
| `growthbook_api_read` | Authenticated GET passthrough to the GrowthBook API |
| `growthbook_api_write` | Authenticated POST/PUT/PATCH/DELETE passthrough |

Competence lives in the [skills](https://github.com/growthbook/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.

## Install / run

```bash
npm install
npm run build
```

Point your MCP client at the compiled entrypoint:

```json
{
  "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:

```bash
npx @growthbook/mcp
```

## Environment variables

| Variable | Required | Default | Purpose |
|----------|----------|---------|---------|
| `GB_API_KEY` | Yes for stdio; optional for HTTP OAuth | — | GrowthBook API key or personal access token |
| `GB_API_URL` | No | `https://api.growthbook.io` | API base URL (self-hosted) and default OAuth AS issuer |
| `GB_MCP_TRANSPORT` | No | `stdio` | `stdio` or `http` |
| `GB_MCP_PORT` | No | `3333` | HTTP listen port (when transport=http) |
| `GB_MCP_HOST` | No | `127.0.0.1` | HTTP bind host |
| `GB_MCP_URL` | Yes for HTTP | — | Public MCP base URL stamped into OAuth resource metadata (server refuses to start in HTTP mode without it) |
| `GB_OAUTH_ISSUER` | No | `GB_API_URL` | GrowthBook OAuth AS issuer URL |
| `GB_HTTP_HEADER_*` | No | — | Extra request headers (e.g. `GB_HTTP_HEADER_CF_ACCESS_TOKEN`) |
| `GB_SKILLS_ENABLED` | No | `true` | Set to `false` / `0` to disable skill tools |

### HTTP + OAuth mode

```bash
OAUTH_AS_ENABLED=1  # on the GrowthBook API
GB_MCP_TRANSPORT=http GB_API_URL=http://localhost:3100 GB_MCP_PORT=3333 npm start
```

Clients connect to:
- `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`)

Unauthenticated requests receive `401` with `WWW-Authenticate` pointing at `/.well-known/oauth-protected-resource`, which advertises the GrowthBook Authorization Server.

Before handling MCP, the server probes GrowthBook REST (`GET /api/v1/`) with the bearer. A `401` from that probe (or later from an API tool) yields HTTP `401` with `error="invalid_token"` so the MCP client can refresh — instead of surfacing `"This API key has expired"` as a tool error. A `403` is treated as an accepted bearer (permission denied ≠ invalid token) so clients are not forced into a refresh loop.

### Capability-only mode

**HTTP (recommended for remote):** point the client at `/mcp/api` instead of `/mcp`:

```json
{
  "mcpServers": {
    "growthbook": {
      "url": "http://127.0.0.1:3333/mcp/api"
    }
  }
}
```

| Path | Tools |
|------|--------|
| `/mcp` | `growthbook_list_skills`, `growthbook_read_skill`, `growthbook_api_read`, `growthbook_api_write` (unless `GB_SKILLS_ENABLED=false`) |
| `/mcp/api` | `growthbook_api_read`, `growthbook_api_write` only |

**stdio / process-wide:** set env so skills are never registered:

```json
"env": {
  "GB_API_KEY": "...",
  "GB_SKILLS_ENABLED": "false"
}
```

When skills are disabled, only the API read/write tools are registered. `growthbook_list_skills` and `growthbook_read_skill` are not exposed.

## How skills are bundled

```bash
npm run build   # tsc && bundle-skills
```

`scripts/bundle-skills.mjs` copies the top-level skill tree from the canonical skills checkout, preserving structure:

```
skills/<skill>/SKILL.md                   → server/skills/<skill>/SKILL.md
skills/<skill>/references/<workflow>.md   → server/skills/<skill>/references/<workflow>.md
```

Source path resolution:

1. `SKILLS_SRC` env var (path to the skills repo root)
2. `agent-skills.local.json` — `{ "path": "../skills" }`, relative to the repo root. Gitignored; copy `agent-skills.local.json.example`
3. `skills-src/` — what CI and the Docker build vendor

There is no implicit sibling lookup. `../skills` resolves to whatever happens to be at that path, which makes a local build silently disagree with the commit CI builds from.

CI, cloud deploys, and releases all read `agent-skills.lock.json` and check out
that exact skills commit. To ship upstream skill changes, update the commit in
the lock file. Local development can point at any checkout with
`agent-skills.local.json` or `SKILLS_SRC`.

The skills repo stays the source of truth — this package does not maintain a
fork of skill content. New skills flow through automatically, except those named
in the small blocklist in `bundle-skills.mjs`. Currently only `gb-setup` is
blocked because it configures the `gb-call` shell adapter rather than GrowthBook
itself.

Per-skill `scripts/` directories are not copied. Relative
`` `references/foo.md` `` links are rewritten to qualified
`` `feature-flags/references/foo` `` paths so `growthbook_read_skill` can resolve
them.

## Using skills with the API tools

Bundled skills still show workflows as:

```bash
gb-call GET /api/v1/projects
gb-call POST /api/v2/features ./payload.json
```

This MCP server does **not** shell out to `gb-call`. Map `GET` → `growthbook_api_read` and `POST`/`PUT`/`PATCH`/`DELETE` → `growthbook_api_write` with the same path and optional JSON body string. Server instructions and `growthbook_read_skill` output include this bridge note.

## Tools detail

### `growthbook_api_read` / `growthbook_api_write`

```json
{ "path": "/api/v1/projects" }
{ "method": "POST", "path": "/api/v2/features", "body": "{\"id\":\"my-flag\",...}" }
```

- Read: GET only (`readOnlyHint: true`)
- Write: `POST` | `PUT` | `PATCH` | `DELETE` (`destructiveHint: true`)
- Returns raw response body on 2xx
- On non-2xx, returns an actionable error (`isError: true`) covering auth failures, self-hosted 404 hints, and rate limits
- Freeform paths target the [GrowthBook REST API](https://docs.growthbook.io/api)

### `growthbook_list_skills` / `growthbook_read_skill`

Only registered when `GB_SKILLS_ENABLED` is not disabled.

- `growthbook_list_skills` returns top-level skill entry points. An entry may contain a complete workflow or route to child workflows.
- `growthbook_read_skill` accepts a listed top-level name or a qualified child path named by a loaded skill (`feature-flags/references/flag-create`) and returns the full markdown (workflow + guardrails).

## Development

```bash
git clone git@github.com:growthbook/skills.git ../skills
cp agent-skills.local.json.example agent-skills.local.json  # edit if not at ../skills

npm install
npm run build
npm start
```

## Standalone HTTP mode

By default the server runs over stdio. Set `GB_MCP_TRANSPORT=http` to run it as a standalone HTTP server that exposes MCP at `/mcp` (skills + API tools) and `/mcp/api` (capability-only), behind an OAuth 2.0 protected-resource surface (RFC 9728 metadata + RFC 6750 `WWW-Authenticate`).

- `GB_MCP_URL` (**required** in HTTP mode) — the server's public base URL. It is stamped into the OAuth resource (audience) and the protected-resource metadata, so it is never derived from request headers. The server refuses to start without it.
- `GB_MCP_PORT` (default `3333`) and `GB_MCP_HOST` (default `127.0.0.1`).
- Incoming bearers are validated by probing the GrowthBook REST API; a rejected token gets HTTP `401` + `WWW-Authenticate` so the client can refresh.

Run it on a trusted network or bound to loopback. For a multi-tenant or public deployment, front it with your own gateway/auth.

## Releases

Cutting a release is deliberate: bump the version in `package.json`, then push a matching `v*` tag:

```bash
git tag v2.0.0
git push origin v2.0.0
```

That tagged commit (with skills frozen at cut time) publishes:

- `@growthbook/mcp` to npm — prereleases (versions with a `-`, e.g. `2.0.0-beta.1`) go under the `beta` dist-tag; stable versions become `latest`
- a multi-arch (`amd64` + `arm64`) image to `ghcr.io/growthbook/growthbook-mcp` (`:<version>`, plus `:<major>`, `:<major>.<minor>`, and `:latest` for stable releases)
- an entry in the MCP registry
- a GitHub Release

Install a release with `npx @growthbook/mcp@<version>` or pull `ghcr.io/growthbook/growthbook-mcp:<version>`.

TDQS

B3/5.0

Scored across 14 tools

Disambiguation4/5

Most tools have distinct purposes, such as create_feature_flag vs. create_force_rule, but there is some overlap between get_feature_flags and get_single_feature_flag, which could cause confusion if an agent needs to fetch a specific flag versus all flags. The descriptions help clarify, but the boundary is not perfectly clear.

Naming Consistency4/5

The naming follows a consistent verb_noun pattern (e.g., create_feature_flag, get_experiments) with minor deviations like generate_flag_types (which uses 'generate' instead of 'get') and search_growthbook_docs (which includes 'growthbook' in the name). Overall, it is mostly predictable and readable.

Tool Count5/5

With 14 tools, the count is well-scoped for a GrowthBook MCP server, covering key operations like creating flags, rules, connections, and fetching various resources. Each tool appears to earn its place without feeling excessive or insufficient for the domain.

Completeness4/5

The tool set provides good coverage for core GrowthBook operations, including CRUD-like actions for features, experiments, and connections, but there are minor gaps such as missing update or delete tools for flags or experiments, which agents might need to work around. The inclusion of search_growthbook_docs adds helpful context.

Maintenance

ActivityActive
ResponsivenessUnresponsive