Critical Risk →

delete_document_by_id

Delete a single document from an index by its internal Searchcraft ID (_id).

How to control delete_document_by_id ↓

What delete_document_by_id does on Searchcraft MCP Server

AI agents call delete_document_by_id to permanently remove resources in Searchcraft MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

Why delete_document_by_id needs a policy

The tool permanently removes data (a document) from a search index using its ID. Deletion is irreversible and cannot be undone, placing it in the Destructive category. Severity is high because an AI agent with access to this tool could maliciously or accidentally delete important indexed documents, and the blast radius depends on what data is in the index and whether backups exist.

From the tool's definition Tool name contains 'delete_document_by_id' and description states 'Delete a single document from an index' — this is an irreversible deletion operation.

Documented attack patterns abuse exactly the kind of access delete_document_by_id gives an agent:

How to control delete_document_by_id

PolicyLayer is an MCP gateway — it sits between your AI agents and Searchcraft MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_document_by_id:

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "delete_document_by_id"
  ]
}

delete_document_by_id disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

  1. Create a free account and register Searchcraft MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RESTRICT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about delete_document_by_id

What does the delete_document_by_id tool do? +

Delete a single document from an index by its internal Searchcraft ID (_id). It is categorised as a Destructive tool in the Searchcraft MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on delete_document_by_id? +

Register the Searchcraft MCP Server MCP server in PolicyLayer and add a rule for delete_document_by_id: 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 Searchcraft MCP Server. Nothing to install.

What risk level is delete_document_by_id? +

delete_document_by_id is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit delete_document_by_id? +

Yes. Add a rate_limit block to the delete_document_by_id 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.

How do I block delete_document_by_id completely? +

Set action: deny in the PolicyLayer policy for delete_document_by_id. 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.

What MCP server provides delete_document_by_id? +

delete_document_by_id is provided by the Searchcraft MCP Server MCP server (searchcraft-inc/searchcraft-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Searchcraft MCP Server tool call.

Start from Searchcraft MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

48 Searchcraft MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.