Low Risk

doc_grep

Regex/keyword search within a single document. Returns matches with

How to control doc_grep ↓

AI agents call doc_grep to retrieve information from MinerU Document Explorer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

doc_grep is a search tool that retrieves matching text from documents without creating, modifying, deleting, or executing operations. It has read-only semantics and minimal blast radius if misused by an AI agent.

From the tool's definition Tool description states 'Regex/keyword search within a single document. Returns matches with' - performs search/retrieval operation with no modification capability.

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

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "doc_grep": {}
  }
}

doc_grep is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register MinerU Document Explorer — 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.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the doc_grep tool do? +

Regex/keyword search within a single document. Returns matches with. It is categorised as a Read tool in the MinerU Document Explorer MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on doc_grep? +

Register the MinerU Document Explorer MCP server in PolicyLayer and add a rule for doc_grep: 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 MinerU Document Explorer. Nothing to install.

What risk level is doc_grep? +

doc_grep is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit doc_grep? +

Yes. Add a rate_limit block to the doc_grep 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 doc_grep completely? +

Set action: deny in the PolicyLayer policy for doc_grep. 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 doc_grep? +

doc_grep is provided by the MinerU Document Explorer MCP server (opendatalab/mineru-document-explorer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MinerU Document Explorer tool call.

Deterministic rules across all 15 MinerU Document Explorer tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

15 MinerU Document Explorer tools catalogued and risk-classified — across an index of 42,500+ 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.