AI agents call web_research to retrieve information from Ruflo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Web research, fact-checking, and item comparison are fundamentally retrieval operations with no side effects. The tool queries external data sources but does not create, modify, delete, execute code, or commit financial transactions. While it could theoretically be used to research sensitive topics, the tool itself has no capability to act on that information beyond returning results.
From the tool's definition Tool name is 'web_research' with description stating 'Search the web, fact-check claims, compare items, or conduct deep research.' These are all read-only operations that retrieve information without modifying external systems.
Attacks that exploit this kind of access
Search the web, fact-check claims, compare items, or conduct deep research. Actions:. It is categorised as a Read tool in the Ruflo MCP Server, which means it retrieves data without modifying state.
Register the Ruflo MCP server in PolicyLayer and add a rule for web_research: 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 Ruflo. Nothing to install.
web_research 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_research 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_research. 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_research is provided by the Ruflo MCP server (ruvnet/ruflo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
web_research is one line of Ruflo's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →