search_knowledge
AI agents call search_knowledge to retrieve information from Fourth Brain Demo 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 a Notion-based marketing knowledge base without modifying it. The naming pattern and server purpose indicate it performs a search operation typical of Read category tools. The empty description lowers confidence slightly, but contextual evidence from the server description and sibling tool patterns strongly suggest read-only retrieval functionality.
From the tool's definition Tool name 'search_knowledge' indicates a search operation; context shows the server provides 'search and retrieval across specialized domains' and 'tools for RAG-style Q&A and content browsing'.
Attacks that exploit this kind of access
search_knowledge. It is categorised as a Read tool in the Fourth Brain Demo MCP Server, which means it retrieves data without modifying state.
Register the Fourth Brain Demo MCP server in PolicyLayer and add a rule for search_knowledge: 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 Fourth Brain Demo. Nothing to install.
search_knowledge 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_knowledge 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_knowledge. 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_knowledge is provided by the Fourth Brain Demo MCP server (rev4nchist/fourth-brain-demo). 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 →