gemini-image-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_MCP_OUT | No | Default save directory | ~/.gemini-image-mcp/images |
| GEMINI_MCP_HOME | No | Profile + state location | ~/.gemini-image-mcp |
| GEMINI_MCP_CHROME | No | Full path to the Chrome executable, if it is not in a standard location (auto-detected by default) | |
| GEMINI_MCP_HEADLESS | No | Set to 0 to watch the browser — useful when selectors break | 1 |
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_generate_imageA | Sends a prompt to gemini.google.com in a headless Chrome signed in with the local Google profile, waits for the generated image(s), saves them to disk and returns the file paths. conversation="continue" keeps the existing chat thread (so you can iterate: "make it darker"); conversation="new" starts a fresh chat. |
| gemini_new_conversationA | Drops the remembered chat thread and opens a fresh one. |
| gemini_session_statusA | Reports whether the local Chrome profile still has a valid Google/Gemini session. If signedIn is false, the user must run "npm run login" in the gemini-image-mcp project and sign in by hand (profile: /root/.gemini-image-mcp/profile). |
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 3 tools
Each tool targets a distinct action: resetting the chat thread, checking session status, and generating images. There is mild overlap since gemini_new_conversation and gemini_generate_image's conversation="new" both start a fresh chat, but descriptions make the distinction clear.
All three tools follow a consistent gemini_<verb>_<noun> snake_case pattern (new_conversation, session_status, generate_image). No deviations in style or casing.
Three tools is slightly lean for the surface, but the server's scope is narrow (image generation via a browser session) and each tool earns its place. No obvious padding or missing operations-driven bloat.
The core lifecycle—verify session, start/continue a conversation, generate and save images—is covered. Login is handled externally via npm run login, so the only minor gap is no tooling around listing or managing previously saved images.