lithtrix_browse · Lithtrix MCP: Risk & Policy

WHAT IT DOES

What lithtrix_browse does on Lithtrix

AI agents invoke lithtrix_browse to trigger actions in Lithtrix. 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.

WHY IT NEEDS A POLICY

Why lithtrix_browse needs a policy

Fetching arbitrary URLs on the server side is an active external operation (Execute) rather than a simple read, as it causes the server to make outbound network requests to third-party destinations. This carries significant blast radius risk: an agent could use it to exfiltrate data, interact with external APIs, trigger webhooks, or access sensitive internal resources via SSRF-like abuse.

From the tool's definition "server-side public web access for agents" — triggers external HTTP requests to arbitrary public URLs on behalf of the agent; "Pay to be fully autonomous" implies active external operations beyond passive data retrieval

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

lithtrix_browse Rate-limited

lithtrix_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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Lithtrix, so you can run agents against it safely.

FAQ

Questions about lithtrix_browse

What does the lithtrix_browse tool do? +

Pay to be fully autonomous: server-side public web access for agents. It is categorised as a Execute tool in the Lithtrix MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on lithtrix_browse? +

Register the Lithtrix MCP server in PolicyLayer and add a rule for lithtrix_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 Lithtrix. Nothing to install.

What risk level is lithtrix_browse? +

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

Can I rate-limit lithtrix_browse? +

Yes. Add a rate_limit block to the lithtrix_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 lithtrix_browse completely? +

Set action: deny in the PolicyLayer policy for lithtrix_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 lithtrix_browse? +

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