workspace-operator-mcp@2.9.0
VERIFIED· not startedPublisher claims: "Deep Google Workspace automation for AI agents — Apps Script execution, local file transfer, Slides, document templates, cross-product search, and tool profiles" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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
GOOGLE_CLIENT_SECRETS_FILEGOOGLE_TOKEN_FILEMCP_AUTH_TOKENConfiguration, not credentials: GOOGLE_BACKUP_DIR, GOOGLE_LOG_FILE, GOOGLE_LOG_LEVEL, MCP_ALLOW_PUBLIC_SHARING, MCP_APPROVAL_BROWSER_WAIT, MCP_APPROVAL_DIR, MCP_APPROVAL_TTL, MCP_APPROVAL_URL, MCP_AUDIT_LOG, MCP_BULK_ALLOW_SHARED_DRIVES, MCP_BULK_DIR, MCP_CONFIG_FILE, MCP_DRY_RUN, MCP_OPERATION_DIR, MCP_OPERATION_TTL, MCP_RETRY_ATTEMPTS, MCP_SCOPE_ROUTING, MCP_TOOL_PROFILE, USERNAME- Where it talks to
- no vendor host named in the code
- What we saw when it ran
- 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. It asks for GOOGLE_CLIENT_SECRETS_FILE, GOOGLE_TOKEN_FILE, MCP_AUTH_TOKEN and talks to its vendor. 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. What the tools do with a real credential was not observed.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 2.2.5
vet-skills diff workspace-operator-mcp 2.2.5 2.9.0In the sandbox, this version reached for nothing 2.2.5 did not. Compared from the two recorded runs, not from source.
- No longer contacted
- google.com
2.2.5 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 2026-11-22 and scored it 83/100 (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 · 0 s · 2 scenarios · 0 deviationsStatic findings
".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.SECRET_NAME_PREFIXES = (".env", "token.json.", "client_secret")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.return subprocess.run( # noqa: S603 - fixed arguments, no shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run( # noqa: S603 # nosec B603 B607Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.for name in ("token.json", ".env", ".env.local", "oauth.keys.json"):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run( # noqa: S603 # nosec B603 B607Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.for path in (".env", "config.yaml", "token.json"):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.for bad in ("../etc/passwd", "op_../../x", "", "op_NOTHEX", "op_123;rm"):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.for char in "\u200b\u200c\u200d\u2060\ufeff\u034f\u00ad"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.self.assertEqual(safe_filename("/etc/passwd"), "passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."token.json", "token.json.bak-1", ".env", ".env.local", "service-account.json",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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.