gemini-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_MODEL | No | Primary model | gemini-flash-latest |
| GEMINI_API_KEY | No | API key (preferred) | |
| GEMINI_RETRIES | No | Retries per model on 429/500/503/network errors | 3 |
| GEMINI_API_KEY_FILE | No | Path to a file holding the key, used only if GEMINI_API_KEY is unset | |
| GEMINI_FALLBACK_MODELS | No | Comma-separated fallbacks (empty = none) | gemini-flash-lite-latest |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| gemini_askA | Ask Google Gemini a question and return its text answer. model: optional model name (default from GEMINI_MODEL or gemini-flash-latest); on rate limits or outages the server retries with backoff, then falls back to GEMINI_FALLBACK_MODELS. system: optional system instruction. |
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 1 tool
With only one tool exposed, there is no possibility of an agent confusing it with another operation. The tool's purpose (forward a question to Gemini and return text) is stated explicitly and clearly.
The single name `gemini_ask` uses a clean snake_case verb_noun form with a server prefix, which is readable and idiomatic. There is no second tool to confirm a pattern, so consistency is trivially satisfied rather than demonstrated.
A single tool is defensible for a narrowly-scoped 'ask Gemini' wrapper, but it is very thin — anything beyond one-shot prompting (chat, model listing, token counting) requires no tool at all. One tool sits at the borderline of feeling under-scoped.
For the literal purpose of asking a question, the surface is complete and even handles retries/fallback models. However, the broader domain (multi-turn conversations, listing available models, streaming or structured output) has no coverage, leaving agents with a single dead-end operation.