google-services-mcp@0.1.103
VERIFIEDPublisher claims: "Gmail MCP server for AI agents — Google Workspace MCP with 100+ tools for Gmail, Calendar, Drive, Docs, Sheets, Meet, and more, multi-account OAuth." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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
EVENT_PAGE_TOKEN_PREFIXGOOGLE_MCP_CLIENT_SECRETConfiguration, not credentials: GOOGLE_MCP_CLIENT_ID, GOOGLE_MCP_DIR, GOOGLE_MCP_REDIRECT_PORT, GOOGLE_MCP_REDIRECT_URI, GOOGLE_MCP_SAVE_ROOT- Where it talks to
- no vendor host named in the codeAlso google.com — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- 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, and read the third-party hosts first. The code names google.com as well as its own vendor. The guard injects EVENT_PAGE_TOKEN_PREFIX, GOOGLE_MCP_CLIENT_SECRET only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 0.1.102
vet-skills diff google-services-mcp 0.1.102 0.1.103In the sandbox, this version reached for nothing 0.1.102 did not. Compared from the two recorded runs, not from source.
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 2026-11-22 and scored it 93/100 (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 · 43 s · 2 scenarios · 0 deviationsStatic findings
No findings across 8,039 lines in 46 files.
Cost to the agent
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.