AI agents call fal-search-models to retrieve information from Mcp Gmail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data (models matching keywords) with no side effects. It performs a search operation that returns results without creating, modifying, deleting, or executing anything. The severity is low because search results alone pose minimal risk unless the returned data itself is sensitive, but typical model searches are informational queries.
From the tool's definition Tool description states 'Search for models by keywords' with 'optional category and limit filtering'. The verb 'search' and the read-only nature of filtering/querying without modification indicate a retrieval operation.
Attacks that exploit this kind of access
Search for models by keywords with optional category and limit filtering. The keywords are used to search for models that match the keywords. It is categorised as a Read tool in the Mcp Gmail MCP Server, which means it retrieves data without modifying state.
Register the Mcp Gmail MCP server in PolicyLayer and add a rule for fal-search-models: 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 Mcp Gmail. Nothing to install.
fal-search-models 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 fal-search-models 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 fal-search-models. 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.
fal-search-models is provided by the Mcp Gmail MCP server (@monsoft/mcp-gmail). 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 →