Search the web using DuckDuckGo. Returns a list of search results
AI agents call web_search to retrieve information from DuckDuckGo MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
web_search retrieves information from the web without creating, modifying, deleting, or executing anything. It is purely a read operation that returns search results. The privacy-focused DuckDuckGo backend and lack of any state-changing operations keep risk minimal. Confidence is high because the description explicitly states it returns search results with no side effects implied.
From the tool's definition Tool performs web search and 'Returns a list of search results' with no modification, deletion, or execution capabilities mentioned. This is a query operation that retrieves data without side effects.
Attacks that exploit this kind of access
Search the web using DuckDuckGo. Returns a list of search results. It is categorised as a Read tool in the DuckDuckGo MCP Server MCP Server, which means it retrieves data without modifying state.
Register the DuckDuckGo MCP Server MCP server in PolicyLayer and add a rule for web_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 DuckDuckGo MCP Server. Nothing to install.
web_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 web_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 web_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.
web_search is provided by the DuckDuckGo MCP Server MCP server (rkampani/duckduckgo-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 →