manage_session

THE RISK

High Risk

Why manage_session needs a policy

This tool controls an autonomous coding agent's execution flow by approving or rejecting plans. Approving a plan triggers Jules to execute potentially large-scale code changes (bug fixes, refactoring, tests) on a repository. The blast radius is high because an AI agent misusing this tool could approve destructive or malicious coding plans, causing significant unintended changes to a codebase.

From the tool's definition Manage an active Jules session: approve or reject plans, or send feedback

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

POLICY

How to control manage_session

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

policy.json

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

manage_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.

Create a free account and register Jules MCP Server — 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

Related tools and policies

More Jules MCP Server tools

Destructive delete_schedule Delete a scheduled task by name Destructive delete_session Delete or cancel an active Jules session Execute create_coding_task Creates a new Jules coding session. Returns immediately with a session ID. Monitor progres Execute create_repoless_task Creates a new Jules session without repository context for scripts, prototypes, or researc Execute schedule_recurring_task Schedule a Jules task to run automatically on a cron schedule. The server manages executio Read wait_for_session Poll a Jules session until it reaches a target state or the timeout expires Read get_activities_since Get session activities newer than a provided ISO timestamp Read get_session_status Get the current status and state of a Jules session

All 11 Jules MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Jules MCP Server → 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.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about manage_session

What does the manage_session tool do? +

Manage an active Jules session: approve or reject plans, or send feedback. It is categorised as a Execute tool in the Jules MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on manage_session? +

Register the Jules MCP Server MCP server in PolicyLayer and add a rule for manage_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 Jules MCP Server. Nothing to install.

What risk level is manage_session? +

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

Can I rate-limit manage_session? +

Yes. Add a rate_limit block to the manage_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 manage_session completely? +

Set action: deny in the PolicyLayer policy for manage_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 manage_session? +

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

Enforce policy on every Jules MCP Server tool call.

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

CHECK YOUR STACK →