Search for documents in the Gallica digital library by subject.
AI agents call search_by_subject to retrieve information from Gallica/BnF MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data from the Gallica digital library based on subject criteria. It has no side effects, cannot modify data, execute code, delete content, or move money. The blast radius of misuse is minimal—an agent could only retrieve unwanted documents or spam search requests, neither of which causes harm to the system or user data.
From the tool's definition Tool performs 'Search for documents' by subject parameter, with no modification, deletion, or execution capabilities mentioned.
Attacks that exploit this kind of access
Search for documents in the Gallica digital library by subject. It is categorised as a Read tool in the Gallica/BnF MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Gallica/BnF MCP Server MCP server in PolicyLayer and add a rule for search_by_subject: 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 Gallica/BnF MCP Server. Nothing to install.
search_by_subject is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_by_subject 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 search_by_subject. 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.
search_by_subject is provided by the Gallica/BnF MCP Server MCP server (ukicar/sweet-bnf). 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 →