Deletes a site row and cascades to its pages and chunks.
AI agents call remove_site to permanently remove resources in Docs — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes documentation site records and all associated data (pages and chunks) from the SQLite database. This is a destructive operation that cannot be undone—deleted data cannot be recovered without a backup. The cascading delete affects multiple related records, amplifying the blast radius.
From the tool's definition Tool description states: 'Deletes a site row and cascades to its pages and chunks.' The use of 'Deletes' and 'cascades' indicates irreversible removal of data and related records.
Attacks that exploit this kind of access
Deletes a site row and cascades to its pages and chunks. It is categorised as a Destructive tool in the Docs MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Docs MCP server in PolicyLayer and add a rule for remove_site: 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 Docs. Nothing to install.
remove_site 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 remove_site 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 remove_site. 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.
remove_site is provided by the Docs MCP server (kage1020/docs-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 →