Jules MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Jules MCP Server Create a session from issue #42 in myorg/myrepo"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Jules MCP Server
MCP (Model Context Protocol) server for Google Jules, the asynchronous AI coding agent. This server enables LLMs to create Jules sessions with automatic pull request creation.
Features
Auto-PR Creation: Sessions automatically create pull requests when complete
Issue Integration: Create sessions directly from GitHub issues
Session Management: List and monitor your Jules sessions
Related MCP server: Jules API MCP
Installation
npm install -g @anthropic/jules-mcpOr run directly with npx:
npx @anthropic/jules-mcpConfiguration
Environment Variables
Variable | Required | Description |
| Yes | Jules API key from Google AI Studio |
| No | GitHub token for fetching issue details (optional but recommended) |
Claude Code
Add to ~/.config/ccs/mcp.toml:
[servers.jules]
command = "npx @anthropic/jules-mcp"
[servers.jules.env]
JULES_API_KEY = "env://JULES_API_KEY"
GITHUB_TOKEN = "env://GITHUB_TOKEN"Claude Desktop
Add to your Claude Desktop config:
{
"mcpServers": {
"jules": {
"command": "npx",
"args": ["@anthropic/jules-mcp"],
"env": {
"JULES_API_KEY": "your-api-key"
}
}
}
}Tools
create_session
Create a new Jules coding session.
Parameters:
repo(required): GitHub repository inowner/repoformatprompt(required): Task description for Julesauto_pr(optional, default: true): Automatically create a PR when donestarting_branch(optional): Branch to start fromtitle(optional): Session title
Example:
{
"repo": "myorg/myrepo",
"prompt": "Add input validation to the login form",
"auto_pr": true
}create_session_from_issue
Create a session directly from a GitHub issue.
Parameters:
repo(required): GitHub repository inowner/repoformatissue_number(required): GitHub issue numberadditional_context(optional): Extra instructions
Example:
{
"repo": "myorg/myrepo",
"issue_number": 42
}list_sessions
List your Jules sessions.
Parameters:
limit(optional, default: 10): Maximum sessions to return
get_session
Get details of a specific session.
Parameters:
session_id(required): The session ID
Development
# Install dependencies
npm install
# Build
npm run build
# Run locally
JULES_API_KEY=your-key node dist/index.jsLicense
MIT
Available Tools
4 toolscreate_sessionA
Create a new Jules coding session. Jules will clone the repo, execute the task, and optionally create a PR automatically.
Inputs: repo (required), prompt (required), title, auto_pr, +1 more.
create_session_from_issueA
Create a Jules session from a GitHub issue. Fetches issue details and creates a session with auto-PR.
Inputs: repo (required), issue_number (required), additional_context.
get_sessionA
Get details of a specific Jules session including status and PR info
Inputs: session_id (required).
list_sessionsA
List your Jules sessions with their status
Inputs: limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
The tools are mostly distinct: list_sessions and get_session clearly separate listing from detail retrieval. However, create_session and create_session_from_issue overlap in purpose, with the latter being a specialization, which could cause minor selection ambiguity.
All tool names follow a consistent verb_noun pattern: create, list, get, create. Even the longer 'create_session_from_issue' maintains the convention with a clear prepositional modifier. There is no mixing of styles or vague verbs.
With exactly 4 tools, the server is well-scoped for its purpose of managing Jules coding sessions. Each tool covers a distinct core operation without redundancy, making the count feel appropriate and not overwhelming.
The tool surface covers session creation (two variants), listing, and retrieval, which handles the primary lifecycle needs. However, it lacks explicit update or delete/cancel operations, which are minor gaps that could be worked around but are not covered.
Maintenance
Related MCP Connectors
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
An MCP server that gives your AI access to the source code and docs of all public github repos
MCP server for generating rough-draft project plans from natural-language prompts.
Related MCP Servers
- AlicenseBqualityDmaintenanceAn MCP server for automating Google Jules that enables seamless integration for task creation, code analysis, and AI-powered development workflows. It supports multiple session modes including Browserbase and cookie-based authentication for both local and cloud environments.1313 npm14MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables users to manage Google's Jules AI coding agent sessions directly from MCP-compatible clients. It supports creating sessions, approving execution plans, and interacting with session activity to streamline autonomous coding workflows.10 npmMIT
- AlicenseAqualityDmaintenanceAn MCP server for orchestrating Google Jules as a remote coding agent from a local coding agent, handling task decomposition, API dispatch, monitoring, intervention, code review, and PR merging.165 npmMIT
- AlicenseAqualityBmaintenanceUnofficial MCP server for Google's Jules AI coding agent that lets AI assistants create and manage asynchronous coding tasks through the Jules API v1alpha.20292 npm2MIT