Low Risk

search_documents

Search through documents using full-text search across content, titles, tags, and metadata. Returns document metadata WITHOUT the full OCR content field to prevent token overflow. Use get_document to retrieve full details for specific documents of interest. Supports Paperless-NGX advanced query s...

How to control search_documents ↓

AI agents call search_documents to retrieve information from Paperless-NGX MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

search_documents performs read-only retrieval of document metadata via full-text search. It queries existing data across content, titles, tags, and metadata without creating, modifying, deleting, or executing any operations. The explicit note that it 'Returns document metadata WITHOUT the full OCR content field' confirms it is a retrieval mechanism.

From the tool's definition Tool name and description both indicate search/query functionality: 'Search through documents using full-text search' and 'Returns document metadata'. No modification, deletion, or execution capabilities described.

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

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

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

search_documents 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 Paperless-NGX 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.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the search_documents tool do? +

Search through documents using full-text search across content, titles, tags, and metadata. Returns document metadata WITHOUT the full OCR content field to prevent token overflow. Use get_document to retrieve full details for specific documents of interest. Supports Paperless-NGX advanced query syntax. It is categorised as a Read tool in the Paperless-NGX MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_documents? +

Register the Paperless-NGX MCP Server MCP server in PolicyLayer and add a rule for search_documents: 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 Paperless-NGX MCP Server. Nothing to install.

What risk level is search_documents? +

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

Can I rate-limit search_documents? +

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

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

search_documents is provided by the Paperless-NGX MCP Server MCP server (nloui/paperless-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Paperless-NGX MCP Server tool call.

Deterministic rules across all 16 Paperless-NGX MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

16 Paperless-NGX MCP Server 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.