gemini-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_MCP_BROWSER | No | Path to browser binary (e.g. /usr/bin/brave-browser). Default is auto-detected. | |
| GEMINI_MCP_PROFILE | No | Chrome/Brave profile folder name to use. | Profile 1 |
| GEMINI_MCP_CDP_PORT | No | Port used for Chrome DevTools Protocol remote debugging. | 9333 |
| GEMINI_MCP_USER_DATA_DIR | No | Path to the browser user data directory. Default is the OS default. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| gemini_statusA | Check the Gemini web session (signed-in Google account, active model, thinking level, and available models). |
| gemini_usageA | Check Gemini quota and usage limits from gemini.google.com/usage, including current usage percentage, reset time, weekly limit, and active plan (Pro / Ultra / Free). |
| gemini_chatA | Send a prompt to Gemini web. Supports switching models ('Argon' / '4 Argon', 'Pro' / '3.1 Pro', 'Flash' / '3.8 Flash', 'Flash-Lite') and setting thinking level ('low', 'medium', 'high'). Waits for response to complete and returns the text. |
| gemini_switch_modelA | Switch the active model ('Argon', 'Pro', 'Flash', 'Flash-Lite') or adjust thinking level without sending a chat message. |
| gemini_new_chatC | Start a fresh chat conversation on Gemini. |
| gemini_upload_and_askB | Upload one or more local files (images, documents, code) to Gemini and ask a question about them. |
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 6 tools
Each tool has a distinct role: status vs usage are separated by session/model info versus quota/limits, and chat/new_chat/switch_model/upload_and_ask are clearly differentiated. The only mild overlap is between gemini_chat and gemini_upload_and_ask, since both send prompts, but the file-upload capability makes the boundary clear enough.
All six tools use a consistent gemini_ prefix with snake_case verb/noun naming (gemini_status, gemini_chat, gemini_new_chat, gemini_usage, gemini_switch_model, gemini_upload_and_ask). The pattern is predictable and readable throughout.
Six tools is well-scoped for a Gemini web-session wrapper, with each tool earning its place across status, chat, reset, usage, model switching, and file upload. There is no obvious redundancy or bloat.
The surface covers the core lifecycle: check status, start a new chat, send prompts, switch models, upload files, and inspect usage. Minor gaps exist around conversation history management (listing or deleting past chats), but core workflows are covered.