Skills/npm/forge-mcp

forge-mcp@0.5.11

VERIFIED· not started

Publisher claims: "MCP server for Laravel Forge — Model Context Protocol integration for AI agents" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher studiometa · publishing for 286 daysInstalls 1,959Last detonated 12 h ago
$claude mcp add forge-mcp -- npx -y @studiometa/forge-mcp
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
OAUTH_SECRETConfiguration, not credentials: FORGE_READ_ONLY
Where it talks to
no vendor host named in the codeAlso laravel.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names laravel.com as well as its own vendor. The guard injects OAUTH_SECRET only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- npx -y @studiometa/forge-mcp

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

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-14 and scored it 81/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 9 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
9.3sprocessdependency install exit 1 · (Use `node --trace-warnings ...` to show where the warning was created) npm error Cannot read properties of null (reading 'edgesOut') npm error A complete log of this run can be found in: /tmp/ks-detonate-tzknfs/task/home/.npm/_logs/2026-11-14T00_41_15_734Z-debug-0.log
9.3sclaimednot started: dependency install failed (exit 1); the server itself was not observed
9.3sprocessscript backend runs setup only
9.3sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsdist/version-CqfPvueB.js:2723 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesupdate: "Replace the entire .env file (provide 'content' field)"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagedist/index.d.ts:9 · npx invocation of non-well-known package — may execute untrusted code* npx @studiometa/forge-mcpFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/server.js:73 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` POST/GET/DELETE http://${displayHost}:${port}/mcp - MCP Streamable HTTP endpoint`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiondist/server.js:82 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` POST http://${displayHost}:${port}/register`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)dist/http.js:1 · MCP server using network transport (SSE/HTTP) — data sent over networkimport { a as SessionManager, i as handleMcpRequest, n as createMcpRequestHandler, r as createMcpServer, t as createHealthApp } from "./http-BGGcUEZT.js";Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
MCP server using network transport (SSE/HTTP)dist/http.d.ts:32 · MCP server using network transport (SSE/HTTP) — data sent over networkexport declare function createMcpServer(options?: HttpServerOptions): Server;Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
npx invocation of non-well-known packagedist/index.d.ts:10 · npx invocation of non-well-known package — may execute untrusted code* npx @studiometa/forge-mcp --read-onlyFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/index.js:136 · npx invocation of non-well-known package — may execute untrusted code* FORGE_READ_ONLY=true npx @studiometa/forge-mcpFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsdist/version-CqfPvueB.js:2719 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdescription: "Manage environment variables (.env file) for a site",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdist/crypto.js:86 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files...credentials,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagedist/index.js:134 · npx invocation of non-well-known package — may execute untrusted code* npx @studiometa/forge-mcpFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsdist/version-CqfPvueB.js:2722 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesget: "Get the current .env file content",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagedist/index.d.ts:11 · npx invocation of non-well-known package — may execute untrusted code* FORGE_READ_ONLY=true npx @studiometa/forge-mcpFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/index.js:135 · npx invocation of non-well-known package — may execute untrusted code* npx @studiometa/forge-mcp --read-onlyFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/server.js:84 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` POST http://${displayHost}:${port}/token`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)dist/server.js:94 · MCP server using network transport (SSE/HTTP) — data sent over network…t.meta.url === `file://${process.argv[1]}` || process.argv[1]?.endsWith("/forge-mcp-server") || process.argv[1]?.endsWith("\\forge-mcp-server")) startHttpServer(Number.parseInt(process.env.PORT || String(DEFAULT_PORT), 10), process.en…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04

Cost to the agent

Instructions loaded
≈4,178 tok
1 file · 59 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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

No advisories in OSV for @studiometa/forge-mcp@0.5.11 as of 12 h ago. This is the package itself, not its dependencies.