invalidate_files
Invalidate (delete from index) specific file paths. Requires KB_ALLOW_WRITE=true. Parameters: paths (list of str).
This record as markdown: /tools/inggerman-mcps/invalidate-files.md
What invalidate_files does on MCP Framework Personal
AI agents call invalidate_files to permanently remove resources in MCP Framework Personal, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why invalidate_files is rated Critical
An AI agent that decides to call invalidate_files doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from MCP Framework Personal is gone. There is no undo for destructive operations.
Attacks that exploit this kind of access
The rule that runs invalidate_files safely
PolicyLayer is an MCP gateway: it sits between your AI agents and MCP Framework Personal, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For invalidate_files, this is the rule to start with:
invalidate_files is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect MCP Framework Personal, apply this rule, and every invalidate_files call is checked against it from then on.
Questions about invalidate_files
Invalidate (delete from index) specific file paths. Requires KB_ALLOW_WRITE=true. Parameters: paths (list of str). It is categorised as a Destructive tool in the MCP Framework Personal MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Framework Personal MCP server in PolicyLayer and add a rule for invalidate_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 MCP Framework Personal. Nothing to install.
invalidate_files is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the invalidate_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 invalidate_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.
invalidate_files is provided by the MCP Framework Personal MCP server (inggerman/mcps). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on MCP Framework Personal, and thousands of servers like it.
Across the catalogue