chatgpt-jules-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JULES_API_KEY | Yes | Your Jules API key |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 14 tools
Tool names are generally distinct with clear actions (get vs list, find vs get) but some pairs like get_activity and list_activities could cause confusion. Without descriptions, an agent might misselect between similar resource-targeting tools.
All tools consistently use snake_case with a verb_noun pattern (e.g., create_session, list_sources). The only exception is health, which is a common standalone name. This pattern aids predictability.
14 tools is well within the ideal 3-15 range for a focused assistant system. Each tool appears to serve a distinct function without redundancy, making the set appropriately scoped.
The surface covers querying and creating sessions, activities, and sources, but lacks update and delete operations for these resources. This leaves gaps that may hinder full lifecycle management.