AI agents call search_mcp_servers to retrieve information from Mcpindex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and presents information from an MCP server index in response to search queries. It has no side effects, cannot modify data, execute code, or cause irreversible changes. The search functionality is a classic Read operation (analogous to a search engine or database query). Severity is low because misuse would at worst return irrelevant search results, with no blast radius beyond that.
From the tool's definition Tool performs "search across the full MCP server registry" and "use when the user knows what tool category they want" — this is a query/lookup operation with no modification or execution capabilities.
Attacks that exploit this kind of access
Keyword + semantic search across the full MCP server registry. Use when the user knows what tool category they want but not which server. It is categorised as a Read tool in the Mcpindex MCP Server, which means it retrieves data without modifying state.
Register the Mcpindex MCP server in PolicyLayer and add a rule for search_mcp_servers: 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 Mcpindex. Nothing to install.
search_mcp_servers 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_servers 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_servers. 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_servers is provided by the Mcpindex MCP server (mcpindex-ai/mcp-server-mcpindex). 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 →