search_knowledge
AI agents call search_knowledge to retrieve information from Sentient Brain Smithery without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'search_knowledge' strongly suggests retrieval of information without modification. Search and query operations are typically read-only with no side effects. However, confidence is moderately lowered due to the absence of a description that could clarify whether this tool has any hidden execute or write capabilities (e.g., if it runs complex queries or triggers indexing operations).
From the tool's definition Tool name 'search_knowledge' indicates a query/search operation. The description is empty, providing no additional detail about potential side effects or operational scope.
Attacks that exploit this kind of access
search_knowledge. It is categorised as a Read tool in the Sentient Brain Smithery MCP Server, which means it retrieves data without modifying state.
Register the Sentient Brain Smithery 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 Sentient Brain Smithery. 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 Sentient Brain Smithery MCP server (mbpfws/sentient-brain-smithery). 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 →