Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DEBUGNoEnable debug mode with screenshotsfalse
TIMEOUTNoBrowser timeout in milliseconds30000
HEADLESSNoRun browser in headless modetrue
COOKIES_PATHNoFile path to save/load cookies~/.jules-mcp/cookies.json
SESSION_MODENoSession management mode: fresh | chrome-profile | cookies | persistent | browserbasefresh
JULES_DATA_PATHNoCustom data storage path~/.jules-mcp/data.json
BROWSERBASE_API_KEYNoYour Browserbase API key for remote browser sessions
GOOGLE_AUTH_COOKIESNoGoogle authentication cookies in string format
CHROME_USER_DATA_DIRNoPath to Chrome profile or custom browser data directory
BROWSERBASE_PROJECT_IDNoYour Browserbase project ID
BROWSERBASE_SESSION_IDNoOptional existing Browserbase session ID

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription
jules_create_taskC

Create a new task in Google Jules with repository and description

jules_get_taskC

Get details of a specific Jules task by ID or URL

jules_list_tasksB

List all Jules tasks with their status

jules_send_messageB

Send a message/instruction to Jules in an active task

jules_approve_planC

Approve Jules execution plan for a task

jules_resume_taskB

Resume a paused Jules task

jules_analyze_codeC

Analyze code changes and diff in a Jules task

jules_bulk_create_tasksB

Create multiple tasks from a list of descriptions and repositories

jules_session_infoA

Get current session configuration and authentication status

jules_setup_wizardC

Interactive session setup wizard for automated Google authentication configuration

jules_get_cookiesB

Extract current browser cookies for session persistence and backup

jules_set_cookiesB

Set browser cookies from string or JSON for authentication

jules_screenshotC

Take a screenshot of current Jules page for debugging and verification

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
Task SchemaComplete task model with all available attributes
Active TasksLive list of active tasks in Jules
Common Task TemplatesTemplate examples for common development tasks
Session Setup AutomationStep-by-step prompts for automated Google authentication setup
Cookie Extraction GuideAutomated prompts for extracting Google authentication cookies
Browserbase ConfigurationAutomated Browserbase setup for remote browser sessions
Session Mode Selection GuideIntelligent guide for choosing the optimal session management mode
Authentication TroubleshootingAutomated diagnostics and fixes for authentication issues

TDQS

A3.6/5.0

Scored across 13 tools

Disambiguation5/5

Every tool has a clearly distinct purpose with no ambiguity. Tools like jules_analyze_code, jules_approve_plan, jules_create_task, and jules_get_task each target specific actions on different aspects of the Jules system, and there is no overlap in functionality that would cause confusion.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with the prefix 'jules_' and snake_case throughout. Examples include jules_create_task, jules_list_tasks, and jules_send_message, making the naming predictable and easy to understand.

Tool Count5/5

With 13 tools, the set is well-scoped for managing Google Jules tasks, covering creation, retrieval, control, and session management. Each tool earns its place without feeling excessive or insufficient for the domain.

Completeness5/5

The tool surface provides complete coverage for the Jules task lifecycle, including create, get, list, approve, resume, and send messages, along with session setup and authentication tools. There are no obvious gaps that would hinder agent workflows.