AI agents call search_documents to retrieve information from Ai Brain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and queries existing documents without creating, modifying, or deleting any data. It is purely informational in nature. The low severity reflects that search operations have minimal blast radius even if misused by an AI agent, as they cannot alter system state or access unauthorized content beyond the search scope already available to the tool's permissions.
From the tool's definition Tool performs 'hybrid full-text + semantic search' to 'find relevant notes' — a retrieval operation with no modification or deletion of data.
Attacks that exploit this kind of access
Hybrid full-text + semantic search within a space. Use this first to find relevant notes by keyword or meaning. It is categorised as a Read tool in the Ai Brain MCP Server, which means it retrieves data without modifying state.
Register the Ai Brain 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 Ai Brain. Nothing to install.
search_documents 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_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.
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.
search_documents is provided by the Ai Brain MCP server (thejoshgriffith/ai-brain). 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 →