AI agents use refresh_index to create or update resources in Eml — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Eml environment.
This tool modifies the search/metadata index by adding new entries, removing stale ones, and updating changed files. While 'remove deleted' suggests some destructive-adjacent behavior, it is removing index entries for already-deleted files (not deleting the files themselves), making this primarily a Write/maintenance operation on the index data structure.
From the tool's definition Incrementally update the index: add new, remove deleted, update changed files
Attacks that exploit this kind of access
Incrementally update the index: add new, remove deleted, update changed files. It is categorised as a Write tool in the Eml MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Eml MCP server in PolicyLayer and add a rule for refresh_index: 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.
refresh_index is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the refresh_index 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 refresh_index. 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.
refresh_index 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 →