AI agents call advanced_search_gallica to retrieve information from Gallica without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a digital library for documents and text retrieval—a read-only operation with no side effects, no code execution, and no data modification. The empty description does not override the clear intent from the tool name and server context.
From the tool's definition Tool name 'advanced_search_gallica' indicates a search operation. Server description explicitly states the tools enable 'searching and accessing OCR text from millions of digitized documents' and lists search capabilities without modifying data.
Attacks that exploit this kind of access
advanced_search_gallica. It is categorised as a Read tool in the Gallica MCP Server, which means it retrieves data without modifying state.
Register the Gallica MCP server in PolicyLayer and add a rule for advanced_search_gallica: 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. Nothing to install.
advanced_search_gallica 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 advanced_search_gallica 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 advanced_search_gallica. 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.
advanced_search_gallica is provided by the Gallica MCP server (nestordemeure/gallica-mcp). 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 →