browse_session · Obscura MCP: Risk & Policy

WHAT IT DOES

What browse_session does on Obscura MCP

AI agents invoke browse_session to trigger actions in Obscura MCP. 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 browse_session needs a policy

This tool triggers and manages external browser operations (navigation, interaction, extraction) via a headless browser. It executes real browser actions against external web resources, making it an Execute-category tool. The blast radius is medium: misuse could drive automated interactions against external sites, but it lacks direct destructive or financial capabilities.

From the tool's definition 'Create and manage persistent browser sessions. Supports multi-step flows: create → goto/wait/extract/click/type → close.'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browse_session Rate-limited

browse_session 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": {
    "browse_session": {
      "limits": [
        {
          "counter": "browse_session_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 Obscura MCP, so you can run agents against it safely.

FAQ

Questions about browse_session

What does the browse_session tool do? +

Create and manage persistent browser sessions. Supports multi-step flows: create → goto/wait/extract/click/type → close. Sessions auto-close after 5 minutes. It is categorised as a Execute tool in the Obscura 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 browse_session? +

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

What risk level is browse_session? +

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

Can I rate-limit browse_session? +

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

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

browse_session is provided by the Obscura MCP server (obscura-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.