Google Jules MCP server
Model Context Protocol server for Google's Jules AI coding agent
2 stars101 downloads/wk
Reviews
Write oneNobody has reviewed Google Jules yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Google Jules tools (20, 7 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
jules_approve_planApprove the execution plan for a Jules session that has requirePlanApproval=true. Only needed when session state is AWAITING_PLAN_APPROVAL. View the plan first with jules_list_activities.
jules_archive_sessionArchive a Jules session to hide it from the default session list without deleting it. Use jules_unarchive_session to restore it.
jules_bulk_create_sessionswrite actionCreate sessions across multiple repositories, reporting each result independently.
jules_cancel_recurring_schedulewrite actionCancel a recurring session schedule.
jules_create_sessionwrite actionStart a new asynchronous coding task with Jules. Provide a detailed task description and the repository to work on. Jules runs in an isolated cloud VM and typically completes tasks in 5-60 minutes depending on complexity.
jules_delete_sessionwrite actionPermanently delete a Jules session. This cannot be undone. Use jules_archive_session instead if you may want the session back later.
jules_execute_and_waitwrite actionCreate a new Jules session and immediately wait/poll for its completion. Automatically tracks progress, emits progress notifications, and returns a unified payload with final state, summary, and PR details upon resolution. Bounded by a wait limit to prevent timeouts.
jules_get_activityGet a single activity from a Jules session by ID. Use jules_list_activities to find activity IDs.
jules_get_session_outputRetrieve the final output and results from a completed Jules session, including pull request details. Use after session state is COMPLETED.
jules_get_sourceGet details for a single GitHub repository connected to Jules, including its branches and visibility. Use jules_list_sources to see all connected repositories.
jules_get_statusCheck the current status and recent activity of a Jules session. Use this to poll for progress and completion. Sessions typically take 5-60 minutes to complete.
jules_list_activitiesGet detailed activity log for a Jules session. Activities include plan generation, progress updates, messages, and completion events. Most recent activities appear first.
jules_list_recurring_schedulesList persistent recurring session schedules.
jules_list_sessionsList all your Jules sessions with their current states. Useful for finding session IDs or checking on multiple tasks.
jules_list_sourcesList all GitHub repositories connected to Jules. You must install the Jules GitHub app at https://jules.google.com before repositories appear here.
jules_list_stuck_sessionsList sessions that are waiting for plan approval or user feedback, following pagination automatically.
jules_schedule_recurring_sessionwrite actionCreate a persistent cron schedule for recurring Jules sessions.
jules_send_messagewrite actionSend a follow-up message or instruction to a running Jules session. Jules will respond in the next activity, which you can see with jules_list_activities or jules_get_status.
jules_unarchive_sessionRestore a previously archived Jules session so it appears in the default session list again.
jules_wait_for_sessionWait/poll for a Jules session to complete. Automatically tracks progress, emits progress notifications, and returns a unified payload with final state, summary, and PR details upon resolution. Bounded by a wait limit to prevent timeouts.
Public scan report
scanner v0.1.9 · 2026-09-20 · same rubric, same numbers if you re-run it
- Code scan49 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 5 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
What the publisher says
From the Google Jules repository's README, as published. We do not edit it. Read it on GitHub
google-jules-mcp-server
If you're searching for a way to drive Google's Jules coding agent from Claude, Cursor, VS Code Copilot, or any other MCP client, this is that bridge. google-jules-mcp-server is an unofficial Model Context Protocol server that exposes the full Jules API (v1alpha) as 13 tools, so your assistant can create sessions, poll status, approve plans, and fetch the resulting pull request without you leaving the chat.
Developers running Jules across many repositories at once use it to let their AI assistant manage the whole async workflow: kick off a task, check on it later, and hand back a PR link when it's done, instead of switching to the Jules web app to babysit progress. Every response is validated at runtime through Zod schemas, so a drifted Jules API response fails loudly rather than silently breaking downstream code.
Model Context Protocol (MCP) server for Google's Jules AI coding agent — unofficial. Lets AI assistants like Claude create and manage asynchronous coding tasks through the Jules API v1alpha.
Overview
Jules is Google's AI coding agent that executes development tasks in isolated cloud VMs — generating code, fixing bugs, writing tests, updating dependencies, and refactoring across files. This server exposes the full Jules API surface as 13 MCP tools, covering repository sources, session lifecycle, and activity logs.
Tasks run asynchronously and typically complete in 5–60 minutes depending on complexity.
Architecture
The server is organized by Jules resource domain rather than as one flat file:
src/
├── index.ts # entrypoint: connects the stdio transport
├── server.ts # createServer(): wires the MCP server + all tool registrations
├── core/ # transport-agnostic: auth, HTTP client, retry/backoff, typed errors, logging
└── resources/
├── sources/ # jules_list_sources, jules_get_source
├── sessions/ # session lifecycle (create/list/status/message/approve/output/delete/archive/unarchive)
└── activities/ # jules_list_activities, jules_get_activityEach resource module owns its own Zod schemas, a typed API client, and its MCP tool registrations. Zod schemas are the single source of truth: TypeScript types are inferred from them (z.infer), and every Jules API response is validated at runtime through core/http-client.ts — so a drifted API response fails loudly as a JulesResponseValidationError instead of silently producing undefineds downstream.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Install directly
Runs npx -y google-jules-mcp-server on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add google-jules-mcp-server -- npx -y google-jules-mcp-server
Google Jules: common questions
- Is Google Jules MCP server safe?
- Mostly: it is graded B (83/100). Read the Google Jules safety report
- How do I install Google Jules?
- It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
- Does Google Jules need an API key?
- Yes. The registry entry asks for
JULES_API_KEY. - Is Google Jules maintained?
- The last commit was 6 days ago (2026-09-15). The latest release is v0.4.0.
- What can I use instead of Google Jules?
- Servers from other publishers that do the same job: Agent-Native Slides MCP server, Orcareplay MCP server and Google Surf MCP server. Compare all Google Jules alternatives.
Alternatives to Google Jules
Same job from other publishers: the closest match first, then the best rated.
- Agent-Native SlidesAgent-Native Google Slides - generate and edit React presentationsnot reviewedEstablishedA
- OrcareplayRead, replay and fork recorded coding-agent runs.not reviewedEstablishedA
- Google SurfWeb, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.not reviewedEstablishedB
- Total Agent MemoryPersistent local memory for coding agents: temporal knowledge graph, procedural and episodic recallnot reviewedEstablishedA
- GitWarrenCode review on your own machine, for you and your coding agent. Nothing leaves your computer.not reviewedEstablishedA