workspace-mcp@2.6.0
VERIFIED· not startedPublisher claims: "Comprehensive, highly performant Google Workspace Streamable HTTP & SSE MCP Server for Calendar, Gmail, Docs, Sheets, Slides & Drive" 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
EXTERNAL_OAUTH21_PROVIDERFASTMCP_SERVER_AUTH_GOOGLE_JWT_SIGNING_KEYGOOGLE_CLIENT_SECRET_PATHGOOGLE_CLIENT_SECRETSGOOGLE_MCP_CREDENTIALS_DIRGOOGLE_OAUTH_CLIENT_IDGOOGLE_OAUTH_CLIENT_SECRETGOOGLE_OAUTH_REDIRECT_URIGOOGLE_PSE_API_KEYMCP_ENABLE_OAUTH21MCP_GITHUB_TOKENMCP_GITHUB_TOKEN_ENV_VAROAUTH_ALLOWED_ORIGINSOAUTH_CUSTOM_REDIRECT_URISOAUTHLIB_INSECURE_TRANSPORTOAUTHLIB_RELAX_TOKEN_SCOPEWORKSPACE_MCP_CREDENTIAL_STORE_BACKENDWORKSPACE_MCP_CREDENTIALS_DIRWORKSPACE_MCP_OAUTH_PROXY_DISK_DIRECTORYWORKSPACE_MCP_OAUTH_PROXY_STORAGE_BACKENDWORKSPACE_MCP_OAUTH_PROXY_VALKEY_HOSTConfiguration, not credentials: DWD_ALLOWED_DOMAINS, FASTMCP_HOME, GATEWAY_IDENTITY_ALGORITHMS, GATEWAY_IDENTITY_AUDIENCE, GATEWAY_IDENTITY_HEADER, GATEWAY_IDENTITY_ISSUER, GATEWAY_IDENTITY_JWKS_URL, GOOGLE_PSE_ENGINE_ID, GOOGLE_SERVICE_ACCOUNT_KEY_FILE, GOOGLE_SERVICE_ACCOUNT_KEY_JSON, MCP_SINGLE_USER_MODE, OTEL_EXPORTER_OTLP_ENDPOINT, OTEL_EXPORTER_OTLP_PROTOCOL, OTEL_EXPORTER_OTLP_TRACES_ENDPOINT, OTEL_EXPORTER_OTLP_TRACES_PROTOCOL, TRUST_GATEWAY_IDENTITY, TWINE_USERNAME, USER_GOOGLE_EMAIL, WORKSPACE_EXTERNAL_URL- Where it talks to
- no vendor host named in the codeAlso google.com, vscode.dev, github.dev, openxmlformats.org, oclc.org, microsoft.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
- 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, vscode.dev, github.dev, openxmlformats.org, oclc.org, microsoft.com as well as its own vendor. The guard injects EXTERNAL_OAUTH21_PROVIDER, FASTMCP_SERVER_AUTH_GOOGLE_JWT_SIGNING_KEY, GOOGLE_CLIENT_SECRET_PATH, GOOGLE_CLIENT_SECRETS, GOOGLE_MCP_CREDENTIALS_DIR, GOOGLE_OAUTH_CLIENT_ID, GOOGLE_OAUTH_CLIENT_SECRET, GOOGLE_OAUTH_REDIRECT_URI, GOOGLE_PSE_API_KEY, MCP_ENABLE_OAUTH21, MCP_GITHUB_TOKEN, MCP_GITHUB_TOKEN_ENV_VAR, OAUTH_ALLOWED_ORIGINS, OAUTH_CUSTOM_REDIRECT_URIS, OAUTHLIB_INSECURE_TRANSPORT, OAUTHLIB_RELAX_TOKEN_SCOPE, WORKSPACE_MCP_CREDENTIAL_STORE_BACKEND, WORKSPACE_MCP_CREDENTIALS_DIR, WORKSPACE_MCP_OAUTH_PROXY_DISK_DIRECTORY, WORKSPACE_MCP_OAUTH_PROXY_STORAGE_BACKEND, WORKSPACE_MCP_OAUTH_PROXY_VALKEY_HOST 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.
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 2026-11-21 and scored it 84/100 (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 · 1 s · 2 scenarios · 0 deviationsStatic findings
base_dir = os.path.join(os.getcwd(), ".credentials")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."""The first PyPI token in the repo's .env, as (variable name, token).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.this run beats the repo's own .env, which beats a file in the homeFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Block .env files and variants (.env, .env.local, .env.production, etc.)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.dotenv_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.DOTENV_PATH = REPO_ROOT / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.dotenv_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.return os.path.join(os.getcwd(), ".credentials")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Stray whitespace from YAML or .env files must not leave local files enabled.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run(command, **kwargs)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.…pace" ~/.claude/skills/managing-google-workspace ``` **ChatGPT** - connect via Developer Mode with the [ChatGPT guide](https://workspacemcp.com/guides/chatgpt-developer-mode…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…pace" ~/.claude/skills/managing-google-workspace ``` **ChatGPT** - connect via Developer Mode with the [ChatGPT guide](https://workspacemcp.com/guides/chatgpt-developer-mode…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.return PypiCredentials(f"${dotenv_var} in .env", _token_env(token))Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(["mcpb", "--version"], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(["twine", "--version"], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.…paign=readme&utm_content=nav-guides)** | Claude Desktop/web Connectors, ChatGPT Developer Mode, and more | | **[FAQ & Troubleshooting](https://workspacemcp.com/welc…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.…paign=readme&utm_content=nav-guides)** | Claude Desktop/web Connectors, ChatGPT Developer Mode, and more | | **[FAQ & Troubleshooting](https://workspacemcp.com/welc…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.(a raw .md, .txt, .pdf, ...): there is nothing to convert, so the bytes uploadFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.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
No advisories in OSV for workspace-mcp@2.6.0 as of 37 min ago. This is the package itself, not its dependencies.