oc_task_start

THE RISK

High Risk

This tool creates or starts executable browser tasks that can perform arbitrary actions in an automated Chrome instance. While the name and description don't specify destructive operations, the ability to launch background browser automation tasks with unspecified parameters constitutes Execute-level risk.

From the tool's definition Tool launches a long-running background task in a real Chrome browser harness. The phrase 'launch a long-running tool as a background task' indicates execution of arbitrary operations whose effects depend on task parameters.

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

HOW TO CONTROL OC_TASK_START

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

policy.json

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

oc_task_start 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 OpenChrome — 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 OpenChrome tools

Destructive cookies Manage browser cookies (get, set, delete, clear). Destructive crawl_cancel Mark a crawl job as cancelled. Returns immediately. Subsequent Destructive element_pick Start or cancel an in-page human element picker overlay. Returns selector, DOM, style, and Destructive oc_checkpoint Save, load, list, or delete automation checkpoints for long-running session continuity. Execute geolocation Set or clear geolocation override. Execute oc_task_cancel Request cancellation of a background task. Best-effort: the runner Execute act Execute multi-step browser actions from a natural language instruction. Parses and runs cl Execute batch_execute Execute JS across multiple tabs in parallel.

All 106 OpenChrome 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 OpenChrome → 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 oc_task_start tool do? +

Create a task-level browser harness envelope, or launch a long-running tool as a background task. Returns a task_id. It is categorised as a Execute tool in the OpenChrome MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on oc_task_start? +

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

What risk level is oc_task_start? +

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

Can I rate-limit oc_task_start? +

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

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

oc_task_start is provided by the OpenChrome MCP server (shaun0927/openchrome). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every OpenChrome tool call.

Deterministic rules across all 106 OpenChrome tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

GOVERN OPENCHROME →

Free to start. No card required.

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

// WHAT OC_TASK_START ON OPENCHROME DOES

// THE RISK

// HOW TO CONTROL OC_TASK_START

// EXPLORE