Search the web for relevant information using DuckDuckGo Search.
AI agents call search_tool to retrieve information from Multi-Server MCP Project without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Web search via DuckDuckGo is a read-only operation that retrieves publicly available information without modifying, deleting, executing code, or affecting financial systems. The blast radius is minimal: incorrect search queries might return irrelevant results, but cannot compromise systems or data integrity. This is a straightforward information retrieval tool.
From the tool's definition Tool description states 'Search the web for relevant information using DuckDuckGo Search' — a query operation with no side effects on data or systems.
Attacks that exploit this kind of access
Search the web for relevant information using DuckDuckGo Search. It is categorised as a Read tool in the Multi-Server MCP Project MCP Server, which means it retrieves data without modifying state.
Register the Multi-Server MCP Project MCP server in PolicyLayer and add a rule for search_tool: 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 Multi-Server MCP Project. Nothing to install.
search_tool 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_tool 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_tool. 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_tool is provided by the Multi-Server MCP Project MCP server (srinikandula/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 →