Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.growthbook/growthbook-mcp

NPM · @GROWTHBOOK/MCP

Thin MCP server for GrowthBook — skill loader + authenticated API passthrough

Available components

−3 this week 90 Trust /100

Last scanned (4 hours ago)

Scores higher than 93% of npm servers

Category Developer Tools

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 30 of 92 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to growthbook/growthbook-mcp). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 30 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability68
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 827 tokens (~206/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management77
  • Stability observed for 23 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 6 Nov 26 +1
    • Security disclosure: unverified → fail ▼ functional
  • 5 Nov 26 0
    • Security disclosure: fail → unverified ▼ functional
  • 4 Nov 26 −4
    • Stability: pass → 0.70 functional
  • 29 Oct 26 0
    • Stability: 0.97 → pass security
  • 28 Oct 26 0
    • Stability: pass → 0.97 functional
  • 22 Oct 26 0
    • Stability: 0.97 → pass security
  • 21 Oct 26 0
    • Stability: pass → 0.97 functional
  • 17 Oct 26 +3
    • Stability: 0.80 → pass security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 6 Nov 2026 · Analysed npm/@growthbook/mcp@2.2.0

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo growthbook/growthbook-mcp
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/growthbook/growthbook-mcp/.github/workflows/publish-mcp.yml@refs/tags/v2.2.0
Rekor log index 3112929999
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:2eeb7c64913dfb99280f403918b958da7db528ef7bfb518cd08b83db369eff82b572a1105b5c9dd99cfc9ae047a8d39d124a6851f752f7274f7ffc4fe

Background: How many MCP packages publish verified provenance →

Dependencies 92 packages
Packages resolved 92
Stale 30
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 4 exposed · ~552 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
growthbook_api_read ~130

Make an authenticated GET request to the GrowthBook REST API. Use path (+ optional query string) exactly as shown in skill workflows that mention gb-call GET. Paths typically start with /api/v1/ or /api/v2/. Returns the raw response body on success. Queries the GrowthBook REST API — see https://docs.growthbook.io/api (OpenAPI: https://api.growthbook.io/api/v1/openapi.yaml).

NameTypeReqDescription
pathstringyesAPI path including query string if needed, e.g. /api/v1/projects or /api/v2/features/my-flag

No output schema declared.

No examples provided.

growthbook_api_write ~179

Make an authenticated mutating request (POST, PUT, PATCH, or DELETE) to the GrowthBook REST API. Use method + path (+ optional JSON body) exactly as shown in skill workflows that mention gb-call with those methods. Paths typically start with /api/v1/ or /api/v2/. Returns the raw response body on success. Mutates the GrowthBook REST API — see https://docs.growthbook.io/api (OpenAPI: https://api.growthbook.io/api/v1/openapi.yaml).

NameTypeReqDescription
bodystring–Optional JSON request body as a string (for POST/PUT/PATCH)
methodstringyesHTTP method
pathstringyesAPI path including query string if needed, e.g. /api/v2/features or /api/v1/experiments/exp_123

No output schema declared.

No examples provided.

growthbook_list_skills ~96

List available top-level GrowthBook skill entry points (name + description). Call growthbook_read_skill with the relevant name. If the returned skill routes to a qualified child path (e.g. feature-flags/references/flag-create), call growthbook_read_skill again with that path. Skills encode how to accomplish GrowthBook tasks well; use growthbook_api_read / growthbook_api_write to execute the REST calls they describe.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

growthbook_read_skill ~147

Return the full markdown content of a GrowthBook skill by path. Pass a top-level name from growthbook_list_skills (e.g. feature-flags), or a qualified child path named by a skill (e.g. feature-flags/references/flag-create). Follow the skill's workflow; when it shows `gb-call <METHOD> <PATH> [body]`, use growthbook_api_read for GET and growthbook_api_write for POST/PUT/PATCH/DELETE.

NameTypeReqDescription
namestringyesTop-level skill name (e.g. feature-flags), or a qualified child path named by a skill (e.g. feature-flags/references/flag-create)

No output schema declared.

No examples provided.

Install

How do I install the io.github.growthbook/growthbook-mcp server?

io.github.growthbook/growthbook-mcp runs locally as an npm package, launched with npx -y @growthbook/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @growthbook/mcp

# add to Claude Code
claude mcp add growthbook-growthbook-mcp -- npx -y @growthbook/mcp
Common questions

What is the io.github.growthbook/growthbook-mcp server?

io.github.growthbook/growthbook-mcp is listed in the public MCP registry as io.github.growthbook/growthbook-mcp. Thin MCP server for GrowthBook, skill loader + authenticated API passthrough. This page covers its npm package (@growthbook/mcp).

Is the io.github.growthbook/growthbook-mcp server safe to use?

io.github.growthbook/growthbook-mcp scores 90 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 6 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.growthbook/growthbook-mcp server expose?

io.github.growthbook/growthbook-mcp exposes 4 tools: growthbook_api_read, growthbook_api_write, growthbook_list_skills, growthbook_read_skill. Their descriptions and schemas cost roughly 552 tokens of context every time the server is loaded.

Is the io.github.growthbook/growthbook-mcp server still maintained?

io.github.growthbook/growthbook-mcp is still listed as active in the MCP registry. We last reached this channel on 6 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.growthbook/growthbook-mcp server under?

io.github.growthbook/growthbook-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the io.github.growthbook/growthbook-mcp server?

VerifyMCP ran 16 checks on io.github.growthbook/growthbook-mcp, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.