jules_send_message

THE RISK

Medium Risk

Why jules_send_message needs a policy

This tool sends a message or instruction to an active task session. It creates/modifies the state of a task by injecting input, which is a Write operation. However, since it sends instructions to an AI agent (Jules) that could then execute code or perform other actions, the actual blast radius depends on what instructions are sent.

From the tool's definition Send a message/instruction to Jules in an active task

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

POLICY

How to control jules_send_message

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "jules_send_message": {
      "limits": [
        {
          "counter": "jules_send_message_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

jules_send_message stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

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

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Google Jules MCP tools

Execute jules_approve_plan Approve Jules execution plan for a task Execute jules_resume_task Resume a paused Jules task Execute jules_setup_wizard Interactive session setup wizard for automated Google authentication configuration Write jules_bulk_create_tasks Create multiple tasks from a list of descriptions and repositories Write jules_create_task Create a new task in Google Jules with repository and description Write jules_set_cookies Set browser cookies from string or JSON for authentication Read jules_analyze_code Analyze code changes and diff in a Jules task Read jules_get_cookies Extract current browser cookies for session persistence and backup

All 13 Google Jules MCP tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about jules_send_message

What does the jules_send_message tool do? +

Send a message/instruction to Jules in an active task. It is categorised as a Write tool in the Google Jules MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on jules_send_message? +

Register the Google Jules MCP server in PolicyLayer and add a rule for jules_send_message: 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 Google Jules MCP. Nothing to install.

What risk level is jules_send_message? +

jules_send_message is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit jules_send_message? +

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

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

jules_send_message is provided by the Google Jules MCP server (samihalawa/google-jules-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Google Jules MCP tool call.

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

CHECK YOUR STACK →