search_web
AI agents call search_web to retrieve information from Deep Research Agent 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 publicly available information with no side effects on any system or data store. Even though the description is absent, the function name and context strongly indicate this is a data retrieval tool. The research pipeline architecture (search → fetch → cluster → report) is characteristic of read-only analysis tools.
From the tool's definition Tool name 'search_web' indicates web searching functionality, which is a read operation. Description is empty, but the name and sibling tools (fetch_and_chunk, cluster_findings, generate_report) confirm this is part of a research pipeline with no write,…
Attacks that exploit this kind of access
search_web. It is categorised as a Read tool in the Deep Research Agent MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Deep Research Agent MCP Server MCP server in PolicyLayer and add a rule for search_web: 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 Deep Research Agent MCP Server. Nothing to install.
search_web 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_web 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_web. 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_web is provided by the Deep Research Agent MCP Server MCP server (melisasvr/deep-research-agent-mcp-server). 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 →