AI agents call search_attachments to retrieve information from Eml without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and searches for attachments within emails based on specified criteria. It performs read-only operations to locate data matching search parameters. While it operates on email data, the action itself is a retrieval/query operation that does not modify, delete, or execute any actions.
From the tool's definition The tool description states it will "Find emails containing attachments matching filename, type, or content hints." The verb "find" and the word "search" in the tool name indicate this is a query operation with no side effects.
Attacks that exploit this kind of access
Find emails containing attachments matching filename, type, or content hints. It is categorised as a Read tool in the Eml MCP Server, which means it retrieves data without modifying state.
Register the Eml MCP server in PolicyLayer and add a rule for search_attachments: 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 Eml. Nothing to install.
search_attachments 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_attachments 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_attachments. 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_attachments is provided by the Eml MCP server (miguelripoll23/eml-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 →