Low Risk

search_by_document_type

search_by_document_type

How to control search_by_document_type ↓

What search_by_document_type does on BnF API Server

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

Low Risk

Why search_by_document_type needs a policy

This tool searches a public digital library by document type classification. It retrieves data without side effects, consistent with the Read category. Tool description is empty, which slightly reduces confidence, but the name pattern and sibling tools strongly suggest read-only search functionality. Severity is low because querying a public library database poses minimal risk even if misused by an AI agent.

From the tool's definition Tool name 'search_by_document_type' combined with server context indicating search functionality across Gallica digital library. Sibling tools (advanced_search, natural_language_search, search_by_author, etc.) are all search/retrieval operations.

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

How to control search_by_document_type

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

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

search_by_document_type 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 BnF API 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.

Related tools and policies

Go deeper

Questions about search_by_document_type

What does the search_by_document_type tool do? +

search_by_document_type. It is categorised as a Read tool in the BnF API Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_by_document_type? +

Register the BnF API Server MCP server in PolicyLayer and add a rule for search_by_document_type: 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 BnF API Server. Nothing to install.

What risk level is search_by_document_type? +

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

Can I rate-limit search_by_document_type? +

Yes. Add a rate_limit block to the search_by_document_type 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_by_document_type completely? +

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

search_by_document_type is provided by the BnF API Server MCP server (kryzo/mcp-bibliotheque_nationale_de_france). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every BnF API Server tool call.

Start from BnF API 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.

8 BnF API 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.