maid_files
AI agents call maid_files to retrieve information from Maid Runner without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Given the MAID Runner context (a validation framework) and the naming convention of sibling tools, 'maid_files' most likely lists or retrieves files for inspection. Without a description, confidence is reduced, but the tool name and server purpose suggest a read-only operation. No evidence of side effects, data modification, or destructive capabilities.
From the tool's definition Tool name 'maid_files' suggests file listing or retrieval. No description provided to clarify intent. Sibling tools (maid_validate, maid_snapshot, maid_get_schema, maid_list_manifests) are read-heavy operations in a validation/testing context, suggesting this…
Attacks that exploit this kind of access
maid_files. It is categorised as a Read tool in the Maid Runner MCP Server, which means it retrieves data without modifying state.
Register the Maid Runner MCP server in PolicyLayer and add a rule for maid_files: 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 Maid Runner. Nothing to install.
maid_files 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 maid_files 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 maid_files. 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.
maid_files is provided by the Maid Runner MCP server (mamertofabian/maid-runner-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 →