Skills/npm/google-docs-mcp

google-docs-mcp@2.1.2

VERIFIED· not started

Publisher claims: "MCP server for Google Docs, Sheets, Drive, Gmail, and Calendar" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher a-bonus · publishing for 268 daysInstalls 14,984Last detonated 9 h ago
$claude mcp add google-docs-mcp -- npx -y @a-bonus/google-docs-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
CREDENTIALS_PATHGOOGLE_CLIENT_SECRETJWT_SIGNING_KEYTOKEN_ENCRYPTION_KEYTOKEN_STOREConfiguration, not credentials: ALLOWED_DOMAINS, BASE_URL, GCLOUD_PROJECT, GOOGLE_CLIENT_ID, GOOGLE_IMPERSONATE_USER, GOOGLE_MCP_PROFILE, MCP_STATELESS, MCP_TOOL_GROUPS, MCP_TRANSPORT, SERVICE_ACCOUNT_PATH
Where it talks to
no vendor host named in the codeAlso google.com, claude.ai, claude.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 google.com, claude.ai, claude.com as well as its own vendor. The guard injects CREDENTIALS_PATH, GOOGLE_CLIENT_SECRET, JWT_SIGNING_KEY, TOKEN_ENCRYPTION_KEY, TOKEN_STORE only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- npx -y @a-bonus/google-docs-mcp

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

What changed since 1.11.3

vet-skills diff google-docs-mcp 1.11.3 2.1.2

This version reaches for something 1.11.3 did not: 1 new credential variable (CREDENTIALS_PATH). Compared from the two recorded runs, not from source.

New credential variables
CREDENTIALS_PATH

1.11.3 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

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; not started: dependency install failed; the server itself was not observed) on 2026-11-18 and scored it 89/100 (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 · 10 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
10sprocessdependency 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-XX3YcT/task/home/.npm/_logs/2026-11-18T20_36_51_074Z-debug-0.log
10sclaimednot started: dependency install failed (exit 1); the server itself was not observed
10sprocessscript backend runs setup only
10sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagedist/index.js:235 · npx invocation of non-well-known package — may execute untrusted code'calls will fail until authorization succeeds. Run `npx @a-bonus/google-docs-mcp auth` ' +Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/auth.js:84 · npx invocation of non-well-known package — may execute untrusted code* 1. GOOGLE_CLIENT_ID + GOOGLE_CLIENT_SECRET env vars (npx / production)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/auth.js:102 · npx invocation of non-well-known package — may execute untrusted code'Then run `npx @a-bonus/google-docs-mcp auth` to authorize.');Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)dist/landingPage.js:38 · MCP server using network transport (SSE/HTTP) — data sent over networkconst configJson = JSON.stringify({ mcpServers: { 'google-docs': { type: 'streamableHttp', url: mcpUrl } } }, null, 2);Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Process kill commanddist/tools/gmail/triageInbox.js:75 · Process kill command — agent can terminate processes// allSettled so a single failed message fetch doesn't kill the wholeFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈55 tok
1 file · 81 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 @a-bonus/google-docs-mcp@2.1.2 as of 8 h ago. This is the package itself, not its dependencies.