third-party-gemini-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_PROXY_API_KEY | Yes | The API key for the proxy. | |
| GEMINI_PROXY_BASE_URL | Yes | The base URL of the OpenAI-compatible proxy, typically includes /v1. |
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_flashA | Gemini Flash text, code and document tasks. Optional file reads and exact edits require explicit workspace_root and relative file allowlists. No shell execution. File writes may be partial on failure. |
| gemini_visionA | Analyze or compare up to four images. Explicit local image paths are read and sent to the configured proxy; URLs are passed to the proxy without local fetching. |
| image_generateA | Generate an image using a dynamically discovered image model. Choose auto, chat or images adapter. Can incur provider charges. URL results are returned without downloading. |
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 has a clearly distinct purpose: text/code/document processing, image analysis, and image generation. No overlap in functionality, so an agent can easily select the right tool.
Two tools use the 'gemini_' prefix (gemini_flash, gemini_vision) while the third uses an action-oriented name (image_generate). This mixed convention is somewhat inconsistent, though each name is still descriptive and understandable.
With only 3 tools, the set is slightly thin but still reasonably scoped for a focused Gemini API wrapper. The tools cover the core text, vision, and generation capabilities without unnecessary bloat.
The tool surface covers the primary Gemini modalities (text, vision, image generation), but could be missing other capabilities like embeddings, audio, or fine-tuning. For a general-purpose MCP server, the current set is functional but not exhaustive.