Search for MCP servers by keyword, category, or use case.
AI agents call percept_recommend to retrieve information from Perceptdot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search operation to discover MCP servers. Search and retrieval operations are classic 'Read' category actions. There are no side effects, no code execution, no data modification, and no destructive operations. The severity is low because misuse (e.g., an agent searching for servers) poses minimal risk—it merely retrieves metadata about available tools.
From the tool's definition Tool name 'percept_recommend' and description 'Search for MCP servers by keyword, category, or use case' indicate a query/search operation that retrieves information about available MCP servers without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Search for MCP servers by keyword, category, or use case. It is categorised as a Read tool in the Perceptdot MCP Server, which means it retrieves data without modifying state.
Register the Perceptdot MCP server in PolicyLayer and add a rule for percept_recommend: 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 Perceptdot. Nothing to install.
percept_recommend 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 percept_recommend 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 percept_recommend. 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.
percept_recommend is provided by the Perceptdot MCP server (perceptdot/percept). 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 →