query_emails_by_keyword
AI agents call query_emails_by_keyword to retrieve information from Fastmail MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries/searches email data without modifying, deleting, or executing external operations. It retrieves information from an inbox based on keyword filters. The read-only nature and bounded scope (searching existing emails) result in low severity and blast radius for accidental misuse.
From the tool's definition Tool name 'query_emails_by_keyword' and server description state the tool 'query[ies] by keyword' and enables 'searching Fastmail inbox emails'.
Attacks that exploit this kind of access
query_emails_by_keyword. It is categorised as a Read tool in the Fastmail MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Fastmail MCP Server MCP server in PolicyLayer and add a rule for query_emails_by_keyword: 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 Fastmail MCP Server. Nothing to install.
query_emails_by_keyword 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 query_emails_by_keyword 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 query_emails_by_keyword. 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.
query_emails_by_keyword is provided by the Fastmail MCP Server MCP server (jeffjjohnston/fastmail-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 →