AI agents call search.endpoints to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward information retrieval tool that searches and returns endpoint metadata based on a query. No side effects occur—it does not create, modify, delete, or execute anything. The natural-language search interface is a discovery mechanism with read-only semantics. Confidence is high because the description clearly indicates a read operation with no destructive or financial implications.
From the tool's definition Tool performs search/query of endpoints to find the right one for a task using natural-language. The description emphasizes discovery and lookup ("Find the right 2s endpoint(s)"), with no modification, deletion, execution, or financial operations mentioned.
Attacks that exploit this kind of access
Find the right 2s endpoint(s) for a task using a natural-language query (e.g. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for search.endpoints: 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. Nothing to install.
search.endpoints 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.endpoints 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.endpoints. 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.endpoints is provided by the MCP server (@2sio/mcp). 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 →