farnsworth_browse

THE RISK

High Risk

This tool triggers an autonomous web browsing agent that performs actions on the internet to achieve arbitrary goals. Unlike a simple read/fetch, an 'intelligent web agent' can interact with web pages (click, fill forms, submit data, authenticate, make purchases, etc.), making it an Execute-category tool with high severity due to its autonomous and open-ended nature.

From the tool's definition 'Use the intelligent web agent to browse the internet to achieve a goal'

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

HOW TO CONTROL FARNSWORTH_BROWSE

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

policy.json

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

farnsworth_browse 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 Farnsworth — 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

More Farnsworth tools

Execute farnsworth_delegate Delegate a task to a specialist agent (code, reasoning, research, or creative). The agent Write farnsworth_project_transfer_knowledge Transfer learnings and knowledge from one project to another. Uses LLM to identify transfe Write farnsworth_evolve Provide feedback to help Farnsworth improve. Positive or negative feedback helps the syste Write farnsworth_project_achieve_milestone Mark a milestone as achieved. Write farnsworth_project_link Link two projects to enable knowledge transfer. Linked projects can share concepts and lea Write farnsworth_remember Store information in memory Write farnsworth_project_add_milestone Add a milestone to a project. Milestones track major project goals and deadlines. Write farnsworth_project_add_task Add a task to a project. Tasks can have dependencies on other tasks.

All 20 Farnsworth tools →

Execute tools on other servers

Frida Game Hacking MCP remove_breakpoint Procmon request_elevation WireMCP capture_packets Pentest Ai run_probe

Go deeper

High-risk tools in Farnsworth → 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.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

What does the farnsworth_browse tool do? +

Use the intelligent web agent to browse the internet to achieve a goal. It is categorised as a Execute tool in the Farnsworth MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on farnsworth_browse? +

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

What risk level is farnsworth_browse? +

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

Can I rate-limit farnsworth_browse? +

Yes. Add a rate_limit block to the farnsworth_browse 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 farnsworth_browse completely? +

Set action: deny in the PolicyLayer policy for farnsworth_browse. 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 farnsworth_browse? +

farnsworth_browse is provided by the Farnsworth MCP server (timowhite88/farnsworth). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Farnsworth tool call.

Deterministic rules across all 20 Farnsworth tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

GOVERN FARNSWORTH →

Free to start. No card required.

20 Farnsworth tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// WHAT FARNSWORTH_BROWSE ON FARNSWORTH DOES

// THE RISK

// HOW TO CONTROL FARNSWORTH_BROWSE

// EXPLORE