AI agents call search_mcp_server to retrieve information from Snak without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves information about available MCP servers from Smithery without modifying, deleting, or executing any operations. It is purely informational and read-only in nature, matching the 'Read' category for tools that retrieve or query data without side effects.
From the tool's definition Tool name is 'search_mcp_server' and description states it 'Search[es] for MCP servers on Smithery using a human readable search request'. This is a query/search operation with no side effects.
Attacks that exploit this kind of access
Search for MCP servers on Smithery using a human readable search request. It is categorised as a Read tool in the Snak MCP Server, which means it retrieves data without modifying state.
Register the Snak MCP server in PolicyLayer and add a rule for search_mcp_server: 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 Snak. Nothing to install.
search_mcp_server 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_mcp_server 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_mcp_server. 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_mcp_server is provided by the Snak MCP server (kasarlabs/snak). 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 →