// SCAN REPORT

Jules MCP Server

26 tools. 10 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 3 Jul 2026

10 can modify or destroy data

16 read-only

26 tools total

Community server · catalogue entry verified 03/07/2026

How to control Jules MCP Server ↓

TOOL MAP

What Jules MCP Server exposes to your agents

Read (16) Write / Execute (9) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Jules MCP Server tools

Destructive · Medium jules_cancel_session Cancelling an active session is a destructive action because it irreversibly terminates the session. Execute · Medium jules_wait_for_completion This tool doesn't directly read data (Read), create/modify data (Write), delete data (Destructive), or move money (Financial). Execute · High jules_approve_plan Approving a plan in this context is not merely a write operation; it triggers downstream execution of AI-generated coding tasks and GitHub synchronization. Execute · High jules_create_and_wait This tool triggers automated AI coding task execution by creating a session and running it to completion.

10 of Jules MCP Server's 26 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Jules MCP Server

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

Deny destructive operations

{
  "jules_cancel_session": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "create_session": {
    "limits": [
      {
        "counter": "create_session_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_bash_outputs": {
    "limits": [
      {
        "counter": "get_bash_outputs_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Jules MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON JULES →

Instant setup, no code required.

FULL CATALOGUE

All 26 Jules MCP Server tools

DESTRUCTIVE 1 tools

Destructive jules_cancel_session Cancels an active Jules session.

EXECUTE 5 tools

Execute jules_approve_plan Approves the current plan for a session. Execute jules_create_and_wait Creates a Jules session AND waits for it to complete in a single operation. Execute jules_quick_task Simplest way to assign a task to Jules with sensible defaults. Execute jules_wait_for_completion Waits for a Jules session to complete (success, failure, or cancellation). Execute send_reply_to_session Interacts with an active Jules session (approving plans or sending messages).

WRITE 4 tools

Write create_session Creates a new Jules session or automated run to perform code tasks. If repo and branch are omitted, creates a Write jules_create_session Creates a new Jules session to perform an asynchronous coding task. Write jules_reject_plan Rejects the current plan for a session and optionally provides feedback. Write jules_send_message Sends a message to an active Jules session.

READ 16 tools

Read get_bash_outputs Get all bash command outputs from a Jules session. Returns commands executed, their stdout/stderr, and exit co Read get_code_review_context Review code changes from a Jules session. Returns a structured summary of what changed, Read get_session_state Get the current status of a Jules session. Acts as a dashboard to determine if Jules is busy, waiting, or fail Read jules_get_latest_activity Gets the most recent activity from a Jules session. Read jules_get_session Gets the current status and details of a Jules session. Read jules_get_session_plan Gets the execution plan from a Jules session. Read jules_get_session_summary Gets a comprehensive summary of a Jules session including status, plan, activities, and outputs. Read jules_get_source Gets details about a specific GitHub repository connected to Jules. Read jules_list_activities Lists all activities (events) in a Jules session. Read jules_list_sessions Lists your Jules sessions with optional pagination. Read jules_list_sources Lists all GitHub repositories connected to your Jules account. Read jules_sync_local_codebase Applies the latest Jules diff to a local git working tree (syncs the codebase). Read jules_wait_for_plan Waits for Jules to generate a plan for a session. Read list_sessions List recent Jules sessions with pagination support. Read query_cache Query the LOCAL CACHE of sessions and activities. Returns only previously synced data (fast, but may be stale) Read show_code_diff Show the actual code diff for files from a Jules session.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Jules MCP Server

Can an AI agent delete data through the Jules MCP Server MCP server? +

Yes. The Jules MCP Server server exposes 1 destructive tools including jules_cancel_session. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Jules MCP Server? +

The Jules MCP Server server has 4 write tools including create_session, jules_create_session, jules_reject_plan. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Jules MCP Server.

How many tools does the Jules MCP Server MCP server expose? +

26 tools across 4 categories: Destructive, Execute, Read, Write. 16 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on Jules MCP Server? +

Register the Jules MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Jules MCP Server tool call.

Deterministic rules across all 26 Jules MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON JULES →

Instant setup, no code required.

26 Jules MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.