AI agents call search_best_practices to retrieve information from Mcp Canon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches a knowledge base to retrieve best practices information. The operation is informational retrieval with no side effects—it reads but does not write, execute, destroy, or move money. Confidence is slightly reduced (0.75 rather than higher) because the description is empty, but the name, sibling tools, and server purpose strongly indicate a read operation.
From the tool's definition Tool is named 'search_best_practices' which indicates querying/searching behavior. Sibling tools 'read_full_guide' and 'search_suitable_guides' are clearly Read operations.
Attacks that exploit this kind of access
search_best_practices. It is categorised as a Read tool in the Mcp Canon MCP Server, which means it retrieves data without modifying state.
Register the Mcp Canon MCP server in PolicyLayer and add a rule for search_best_practices: 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 Mcp Canon. Nothing to install.
search_best_practices 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_best_practices 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_best_practices. 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_best_practices is provided by the Mcp Canon MCP server (tripcher/canon). 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 →