Search Gmail messages and return metadata.
AI agents call gmail_search to retrieve information from AIOS Co-Founder MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data from Gmail without creating, modifying, deleting, or executing any actions. Searching for messages and returning metadata is a passive read operation. Even though Gmail can contain sensitive personal information, the tool itself performs no destructive or mutative operations, placing it in the Read category with low severity.
From the tool's definition Tool description states 'Search Gmail messages and return metadata.' The verb 'search' and the specification that it returns 'metadata' indicate a read-only operation with no side effects.
Attacks that exploit this kind of access
Search Gmail messages and return metadata. It is categorised as a Read tool in the AIOS Co-Founder MCP MCP Server, which means it retrieves data without modifying state.
Register the AIOS Co-Founder MCP server in PolicyLayer and add a rule for gmail_search: 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 AIOS Co-Founder MCP. Nothing to install.
gmail_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the gmail_search 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 gmail_search. 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.
gmail_search is provided by the AIOS Co-Founder MCP server (varun-b-nagaraj/python-mcp-server). 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 →