AI agents use close_mdf to create or update resources in Mdfmcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mdfmcp environment.
Closing an MDF session modifies the state of an open resource by terminating it and releasing associated memory/handles. This is a reversible state-changing operation (the session can be reopened with open_mdf), distinct from destructive deletion. It does not read data (Read), execute arbitrary code (Execute), permanently delete data (Destructive), or handle money (Financial).
From the tool's definition Tool name 'close_mdf' and description 'Close an MDF session and free resources' indicate closing/terminating an active session state.
Attacks that exploit this kind of access
Close an MDF session and free resources. It is categorised as a Write tool in the Mdfmcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mdf MCP server in PolicyLayer and add a rule for close_mdf: 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 Mdfmcp. Nothing to install.
close_mdf 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 close_mdf 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 close_mdf. 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.
close_mdf is provided by the Mdf MCP server (shanko-26/mdfmcp). 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 →