GeminiSAFE
MCP server implementation for Google's Gemini API
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/server/mcp-server-gemini) [](https://www.npmjs.com/package/mcp-server-gemini) [](https://opensource.org/licenses/MIT) [](https://www.typescriptlang.org/) [](https://modelcontextprotocol.io/)
A powerful MCP (Model Context Protocol) server that brings Google's latest Gemini AI models to your favorite development environment. Access Gemini 2.5's thinking capabilities, vision analysis, embeddings, and more through a seamless integration.
🚀 Works with: Claude Desktop, Cursor, Windsurf, and any MCP-compatible client 🎯 Why use this: Get Gemini's cutting-edge AI features directly in your IDE with full parameter control 📚 Self-documenting: Built-in help system means you never need to leave your editor
Features
- 6 Powerful Tools: Text generation, image analysis, token counting, model listing, embeddings, and self-documenting help
- Latest Gemini Models: Support for Gemini 2.5 series with thinking capabilities
- Advanced Features: JSON mode, Google Search grounding, system instructions, conversation memory
- Full MCP Protocol: Standard stdio communication for seamless integration with any MCP client
- Self-Documenting: Built-in help system - no external docs needed
- TypeScript & ESM: Modern, type-safe implementation
Supported Models
ad33058d6ccdOBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-server-gemini --env GEMINI_API_KEY=${GEMINI_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"mcp-server-gemini": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"GEMINI_API_KEY": "${GEMINI_API_KEY}"
}
}
}
}Exposed tools (17)
17 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Examples | read | Example usage patterns for common tasks |
analyze_image | read | Analyze images using Gemini vision capabilities |
code | read | Code to review |
code_review | read | Comprehensive code review with Gemini 2.5 Pro |
count_tokens | read | Count tokens for a given text with a specific model |
creative_writing | read | Creative writing with style control |
embed_text | read | Generate embeddings for text using Gemini embedding models |
explain_with_thinking | read | Deep explanation using Gemini 2.5 thinking capabilities |
generate_text | read | Generate text using Google Gemini with advanced features |
get_help | read | Get help and usage information for the Gemini MCP server |
language | read | Programming language |
length | read | Desired length |
level | read | Explanation level (beginner/intermediate/expert) |
list_models | read | List all available Gemini models and their capabilities |
prompt | read | Writing prompt |
style | read | Writing style |
topic | read | Topic to explain |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@google/genai, @types/jest, @types/node, @typescript-eslint/eslint-plugin, @typescript-eslint/parser, eslint, jest, prettier
Gates applied: no_behavioural_pass.
ad33058d6ccdfull audit observations/trust-audit/mcp-server/aliargun__gemini-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | ad33058d6ccd | SAFE | B | 89 | first audit |
Questions
What is the Gemini MCP server?
MCP server implementation for Google's Gemini API
What tools does Gemini expose?
17 in total: 17 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Gemini safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Gemini need?
It reads GEMINI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (ad33058d6ccd), read on 2026-10-06. The repository is watched and re-audited when it changes.