search_and_fetch
AI agents call search_and_fetch to retrieve information from DuckDuckGo Web Search MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs information retrieval operations (web search and content fetching) with no capability to modify, delete, or execute code. It is a pure read operation that queries external data sources and returns results. Low severity due to minimal blast radius—misuse returns irrelevant search results but cannot harm systems or data.
From the tool's definition Server description indicates it 'search[es] the web using DuckDuckGo and optionally fetch[es] and summarize[s] content from search results.' The tool name 'search_and_fetch' combines read-only operations (searching and retrieving web content).
Attacks that exploit this kind of access
search_and_fetch. It is categorised as a Read tool in the DuckDuckGo Web Search MCP Server MCP Server, which means it retrieves data without modifying state.
Register the DuckDuckGo Web Search MCP Server MCP server in PolicyLayer and add a rule for search_and_fetch: 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 Web Search MCP Server. Nothing to install.
search_and_fetch 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_and_fetch 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_and_fetch. 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_and_fetch is provided by the DuckDuckGo Web Search MCP Server MCP server (kouui/web-search-duckduckgo). 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 →