Execute deep research on a topic with progress tracking. Args: topic: The research topic or question to investigate max_searches: Maximum number of web searches (default from settings) save_to_file: Optional file path to save the report Returns: The research report as markdown
AI agents invoke run_deep_research to trigger actions in Browser-Use MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers execution of research workflows including automated web searches and file operations. While not destructive, the ability to perform arbitrary web searches and write files based on user-supplied topic arguments represents an Execute category risk—the consequences depend entirely on what topic an AI agent provides.
From the tool's definition Tool description states 'Execute deep research on a topic' with 'maximum number of web searches' and optional file writes.
Documented attack patterns abuse exactly the kind of access run_deep_research gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Browser-Use MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for run_deep_research:
{
"version": "1",
"default": "deny",
"tools": {
"run_deep_research": {
"limits": [
{
"counter": "run_deep_research_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_deep_research stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute deep research on a topic with progress tracking. Args: topic: The research topic or question to investigate max_searches: Maximum number of web searches (default from settings) save_to_file: Optional file path to save the report Returns: The research report as markdown. It is categorised as a Execute tool in the Browser-Use MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Browser-Use MCP Server MCP server in PolicyLayer and add a rule for run_deep_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 Browser-Use MCP Server. Nothing to install.
run_deep_research is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_deep_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 run_deep_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.
run_deep_research is provided by the Browser-Use MCP Server MCP server (saik0s/mcp-browser-use). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 Browser-Use MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
9 Browser-Use MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.