run_browsing_task

THE RISK

High Risk

Why run_browsing_task needs a policy

This tool runs code-like operations (browser navigation and interaction) whose effects depend on the task arguments provided. While it may retrieve data, its primary function is to execute browser actions, which can modify state on external websites, interact with forms, submit data, or trigger unintended side effects. This is classic Execute category behavior.

From the tool's definition Tool name 'run_browsing_task' and description 'Execute a one-time web browsing task. The navigator agent runs a browser' explicitly indicate execution of browser automation, which can perform arbitrary actions on web pages.

Documented attack patterns abuse exactly the kind of access run_browsing_task gives an agent:

POLICY

How to control run_browsing_task

PolicyLayer is an MCP gateway — it sits between your AI agents and Yutori MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for run_browsing_task:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_browsing_task": {
      "limits": [
        {
          "counter": "run_browsing_task_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

run_browsing_task 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.

Create a free account and register Yutori MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Yutori MCP tools

Destructive delete_scout Permanently delete a scout and all its data. This action cannot be undone. Execute run_research_task Execute a one-time deep web research task. The research agent searches, Write create_scout Create a monitoring scout for continuous web monitoring. Scouts track changes relevant to Write edit_scout Update an existing scout Read get_browsing_task_result Poll for browsing task status and result. Call until status is Read get_research_task_result Poll for research task status and result. Call until status is Read get_scout_detail Get detailed information about a specific scout. Read get_scout_updates Get paginated updates/reports for a scout. Each update contains findings from a run.

All 11 Yutori MCP tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Yutori MCP → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about run_browsing_task

What does the run_browsing_task tool do? +

Execute a one-time web browsing task. The navigator agent runs a browser and. It is categorised as a Execute tool in the Yutori MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_browsing_task? +

Register the Yutori MCP server in PolicyLayer and add a rule for run_browsing_task: 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 Yutori MCP. Nothing to install.

What risk level is run_browsing_task? +

run_browsing_task is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_browsing_task? +

Yes. Add a rate_limit block to the run_browsing_task 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.

How do I block run_browsing_task completely? +

Set action: deny in the PolicyLayer policy for run_browsing_task. 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.

What MCP server provides run_browsing_task? +

run_browsing_task is provided by the Yutori MCP server (yutori-ai/yutori-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Yutori MCP tool call.

Start from Yutori MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →