Skills/npm/mcp-server

mcp-server@3.20.0

VERIFIED

Publisher claims: "Approve plans, track initiatives and work items, and steer AI engineering crews in AnyForge." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher anyforge · publishing for 171 daysInstalls 4,985Last detonated 21 min ago
$claude mcp add mcp-server -- npx -y @anyforge/mcp-server
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
ANYFORGE_API_TOKENConfiguration, not credentials: ANYFORGE_API_URL
Where it talks to
anyforge.ai (its own)
What the honeypot saw
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Connect it with a scoped credential, under the guard. It asks for ANYFORGE_API_TOKEN and talks to anyforge.ai. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind.

$vet-skills run --secrets ANYFORGE_API_TOKEN=anyforge.ai -- npx -y @anyforge/mcp-server

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 3.19.0

vet-skills diff mcp-server 3.19.0 3.20.0

This version reaches for something 3.19.0 did not: 1 new tool (anyforge_get_work_summary) · 1 rewritten tool descriptor (anyforge_list_work_items). Compared from the two recorded runs, not from source.

New tools
anyforge_get_work_summary
Rewritten tool descriptors
anyforge_list_work_items
Tools removed
anyforge_update_my_availability

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-17 and scored it 90/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 28 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
8.0sprocessdependency install exit 0
28sclaimed270 tools: anyforge_branch_studio_session, anyforge_rewind_studio_session, anyforge_update_studio_review_finding, anyforge_get_studio_pr_comments, anyforge_get_studio_pr_jobs, anyforge_get_studio_pr_logs, anyforge_request_studio_review, anyforge_list_studio_crew_batches, anyforge_get_studio_crew_batch, anyforge_preview_studio_crew_batch, anyforge_cancel_studio_crew_batch, anyforge_retry_studio_crew_batch, anyforge_list_studio_sessions, anyforge_create_studio_session, anyforge_get_studio_usage, anyforge_get_studio_session, anyforge_update_studio_session, anyforge_get_studio_context, anyforge_add_studio_context, anyforge_list_studio_runs, anyforge_start_studio_run, anyforge_get_studio_run, anyforge_get_studio_run_events, anyforge_control_studio_run, anyforge_get_studio_changes
28stoolsb07b77188f8c78a5
28stools1f8655193bfd5561
28stools0cb88e0fb427a4ff
28stools7d524336e50c1ffd
28stools44206e02eea2984d
28stools93f05a82ee025b72
28stools5e4ac021080bd0f5
28stools4bb94b8b8304197e
28stoolsbfbd02e676a35573
28stoolse471a667dc4036b8
28stools711032bfeb67221a
28stoolsd6af9c17e14eacf8
28stools0978777fa186217c
28stools30f59d7cf2186ed6
28stoolse147662dd1a2372c
28stools540cc1c71c209481
28stools328f3348d1a1ad89
28stools3691dc8653180945
28stools27a62d73cf3d6254
28stools29d6688b3cfa2148
28stoolsaf373a39a63e8d87
28stools6a53cd21a1cb42dd
28stools3cc9c01736b9d944
28stools80e3bcb50e5924af
28stoolscc07565f9c928037
28stoolsf208306398d36329
28stoolsec056fa83d86d6ed
28stoolsb5e63e97883d32b8
28stoolse6bd9df7852a1f35
28stools290125fc45f18376
28stools4e5283c7801f37e5
28stools65d38b7593fed2d7
28stools344fef03a1d02d9d
28stools1e0a81319e2cd913
28stoolsa7ffa9388c8f9795
28stools0fa2cf5e8127ee36
28stools101d127c1a276727
28stools3f73b65ec3dd4b6b
28stools7ddb95b00f686d9e
28stools47c41382c572f6ba
28stoolsbe9d0917e70daaf5
28stoolsff60f4690ba0a678
28stools102e5561b00c80c4
28stools443386bbda625b1c
28stools0f02024fb341cbfd
28stoolsdeef39d189ec81aa
28stools07ccfcb4b250aaf5
28stools85af972e7bacc207
28stools6538949298dde656
28stools9a77f39e684d9b1b
28stools467f21ae72f9740a
28stools279364e0ff34e9db
28stools14cde611007e39a7
28stools4a74494e1d2749eb
28stools324fb26b6c635fae
28stoolscba612aacd86794a
28stoolsaf479a3aefc9277e
28stoolsa275b607ecdf8b32
28stools012b8ad7e9d9b8fd
28stoolsac0844c50baf6a6a
28stools9786b56afcc51c48
28stoolsba5b89de1b6a2e70
28stoolsad2e5a4bf2c31bdd
28stools9ed9c945fa70b76b
28stoolsabd4aaf670f44209
28stoolse0411540f3175a15
28stoolsd40fbbb7aab06b84
28stools1ed891c44764d630
28stools6210ceaa12f1786a
28stoolsad7375c19e98ceee
28stools11a06bd46611bbee
28stools6cdac236ef958000
28stools4b3e25668a4dec33
28stools725a3932445e911b
28stoolsc9415b0538c9f56c
28stoolsca2ba85981fb77f2
28stools580ccf184b591252
28stools6bf39571d8f399e2
28stools8d3a1d9b175903e3
28stools3d70c7c5b2f40b3c
28sprocessscript backend runs setup only
28sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actiondist/index.js:15 · File type combined with upload action — agent may exfiltrate local data files…eads the repo tree for a checked-in coverage report (lcov.info, coverage-summary.json, cobertura, clover) and records the parsed %, so a repo that publishes coverage in git shows a number without a crew run or a manual upload. Runs in the …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagedist/index.js:2 · npx invocation of non-well-known package — may execute untrusted code…ndpoint:t||r.endpoint||Bt};throw new Error("No AnyForge credentials found. Run `npx @anyforge/control init` to authorise this machine, or set ANYFORGE_API_TOKEN (and optionally ANYF…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/index.js:3 · File type combined with upload action — agent may exfiltrate local data files…tore()}:{},...Gt(e)},...r!==void 0?{body:JSON.stringify(r)}:{}}),u;try{u=await m.json()}catch{throw new f("invalid_response",m.status,`non-JSON response from ${p}`)}if(!m.ok||u.ok===!1)throw Jt(u,m.status);return u.data}function Jt(e,t){le…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈71 tok
1 file · 4 in bundle
Tool list per prompt
≈94,592 tok
270 tools · 350 per tool
Handshake
13922 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 445

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.