gemini-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_MODEL | No | Default model to use with Gemini | gemini-3-pro-preview |
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 | {} |
| logging | {} |
| prompts | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| geminiA | Query Gemini AI. Supports model selection, sandbox mode for safe code execution, and structured change mode for applying edits. |
| web-searchA | Search the web using Gemini with Google Search grounding for real-time information. |
| analyze-mediaA | Analyze images, PDFs, or other media files using Gemini multimodal capabilities. Supports screenshots, diagrams, documents, and more. |
| shellA | Generate and optionally execute shell commands using Gemini. By default runs in dry-run mode (explains commands). Set dryRun=false to execute in sandbox. |
| brainstormA | Generate creative ideas using structured frameworks (SCAMPER, Design Thinking, etc.) with domain context, feasibility analysis, and iterative refinement. |
| fetch-chunkA | Retrieves cached chunks from a changeMode response. Use this to get subsequent chunks after receiving a partial changeMode response. |
| pingA | Test connectivity by echoing a message back. |
| helpA | Display Gemini CLI help and available options. |
| timeout-testB | Test timeout prevention by running for a specified duration |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| gemini | Query Gemini AI with optional sandbox execution and structured change mode. |
| web-search | Search the web for real-time information using Google Search grounding. |
| analyze-media | Analyze media files (images, PDFs) using Gemini multimodal AI |
| shell | Generate shell commands for a task, optionally executing in sandbox mode |
| brainstorm | Generate creative ideas using structured brainstorming methodologies. |
| fetch-chunk | Fetch the next chunk of a response |
| ping | Echo a test message to verify connectivity. |
| help | Display Gemini CLI help information. |
| timeout-test | Test the timeout prevention system by running a long operation |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool has a clearly distinct purpose: general query, web search, media analysis, shell command, brainstorming, chunk retrieval, connectivity test, help, and timeout test. No two tools appear to overlap in functionality.
Most tools follow a lowercase hyphenated verb-noun pattern (e.g., web-search, analyze-media, fetch-chunk), but a few are single-word nouns or verbs (gemini, shell, ping, help, timeout-test), creating minor inconsistency.
With 9 tools, the server covers core capabilities without being overwhelming. The count is well-scoped for an AI assistant providing querying, search, media analysis, shell execution, brainstorming, and utilities.
The tool set covers major interaction modes: querying, web search, media analysis, shell commands, brainstorming, and utility functions. The fetch-chunk tool addresses a specific need, but there are no obvious gaps for the stated domain.