Search stub documents and return minimal results (id, title, url)
AI agents call search to retrieve information from MCP Server Starter 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 query that returns document metadata (id, title, url). It is a read-only operation with no destructive, executable, or financial implications. The minimal blast radius and passive nature justify 'low' severity.
From the tool's definition Tool description explicitly states 'Search stub documents and return minimal results (id, title, url)' — a query operation that retrieves data without modification or side effects.
Attacks that exploit this kind of access
Search stub documents and return minimal results (id, title, url). It is categorised as a Read tool in the MCP Server Starter MCP Server, which means it retrieves data without modifying state.
Register the MCP Server Starter MCP server in PolicyLayer and add a rule for search: 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 Server Starter. Nothing to install.
search 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 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. 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 is provided by the MCP Server Starter MCP server (lassiterj/mcp-playground). 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 →