AI agents call search_content to retrieve information from Mdbook 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 an mdbook project without modifying, deleting, or executing anything. It is a straightforward search operation that returns matching content. The blast radius of misuse is minimal—an AI agent searching content cannot cause harm beyond potentially exposing sensitive information already present in the mdbook, which is a low-risk read operation.
From the tool's definition Tool name is 'search_content' and description states 'Search for content in the mdbook project' — a read-only query operation with no side effects.
Attacks that exploit this kind of access
Search for content in the mdbook project. It is categorised as a Read tool in the Mdbook MCP Server, which means it retrieves data without modifying state.
Register the Mdbook MCP server in PolicyLayer and add a rule for search_content: 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 Mdbook. Nothing to install.
search_content 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_content 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_content. 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_content is provided by the Mdbook MCP server (mdbook-mcp-server). 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 →