Authenticate a Google account. Opens a browser for OAuth consent. Use this to add a new account or re-authenticate an existing one.
AI agents invoke google_auth to trigger actions in Mariana Google MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an external browser-based OAuth flow, which is an external operation with side effects (granting access tokens, adding/modifying authenticated account sessions). It goes beyond a simple read and involves executing an OAuth authentication process that modifies system state (stored credentials/tokens).
From the tool's definition Opens a browser for OAuth consent. Use this to add a new account or re-authenticate an existing one.
Attacks that exploit this kind of access
Authenticate a Google account. Opens a browser for OAuth consent. Use this to add a new account or re-authenticate an existing one. It is categorised as a Execute tool in the Mariana Google MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mariana Google MCP server in PolicyLayer and add a rule for google_auth: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mariana Google MCP. Nothing to install.
google_auth is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the google_auth rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for google_auth. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
google_auth is provided by the Mariana Google MCP server (marianasmall/mariana-google-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →