AI agents call search_mail to retrieve information from Tbird without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool searches mail, which is a query operation with no side effects. It retrieves data from local mbox files without modifying, deleting, or executing any operations. The empty description is compensated by the clear context from the server's stated purpose and sibling tools that all perform read-only operations.
From the tool's definition Tool name 'search_mail' combined with server description stating it 'Reads and searches Thunderbird mail from local mbox files'. Sibling tools include 'list_accounts', 'list_folders', 'read_message', and 'extract_attachments', all clearly read-only operations.
Attacks that exploit this kind of access
search_mail. It is categorised as a Read tool in the Tbird MCP Server, which means it retrieves data without modifying state.
Register the Tbird MCP server in PolicyLayer and add a rule for search_mail: 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 Tbird. Nothing to install.
search_mail 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 search_mail 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 search_mail. 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.
search_mail is provided by the Tbird MCP server (neil-zielsdorf/tbird-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 →