Gemini CLICAUTION
MCP server that enables AI assistants to interact with Google Gemini CLI, leveraging Gemini's massive token window for large file analysis and codebase understanding
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/jamubc/gemini-mcp-tool/releases) [](https://www.npmjs.com/package/gemini-mcp-tool) [](https://www.npmjs.com/package/gemini-mcp-tool) [](https://opensource.org/licenses/MIT) [](https://github.com/jamubc/gemini-mcp-tool)
📚 [View Full Documentation](https://jamubc.github.io/gemini-mcp-tool/) - Search me!, Examples, FAQ, Troubleshooting, Best Practices
This is a simple Model Context Protocol (MCP) server that allows AI assistants to interact with the Gemini CLI. It enables the AI to leverage the power of Gemini's massive token window for large analysis, especially with large files and codebases using the @ syntax for direction.
- Ask gemini natural questions, through claude or Brainstorm new ideas in a party of 3!
TLDR: [](#) + [](#)([](#))
Goal: Use Gemini's powerful analysis capabilities directly in Claude Code to save tokens and analyze large files.
Prerequisites
🚀 Important: Gemini CLI is retired. This tool now defaults to Antigravity CLI (agy)
O
40c3845fea8aOBSERVED · 2026-09-23Connect
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 gemini-mcp-tool --env DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY} --env OPENROUTER_API_KEY=${OPENROUTER_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"gemini-mcp-tool": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"DEEPSEEK_API_KEY": "${DEEPSEEK_API_KEY}",
"OPENROUTER_API_KEY": "${OPENROUTER_API_KEY}"
}
}
}
}Exposed tools (9)
9 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Help | read | receive help information |
ask-gemini | read | model selection [-m], sandbox [-s], and changeMode:boolean for providing edits |
brainstorm | read | Generate novel ideas with dynamic context gathering. --> Creative frameworks (SCAMPER, Design Thinking, etc.), domain context integration, idea clustering, feasibility analysis, and iterative refinement. |
fetch-chunk | read | Retrieves cached chunks from a changeMode response. Use this to get subsequent chunks after receiving a partial changeMode response. |
message | read | Message to test with |
ping | read | Echo |
prompt | read | fetch-chunk cacheKey=<key> chunkIndex=<number> |
test-tool | read | A test tool demonstrating the simplified registration |
timeout-test | read | Test timeout prevention by running for a specified duration |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | WARN |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- declared (5 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (9)
tagline: "Leverage Google's Gemini models in any client that supports the standardized MCP protocol—<span style='color: #FFFFFF; background-color: #D97706; padding: 2px 8px; border-radius: 6px; font-s
assert.throws(() => assertSafeFileReferences("@~/.ssh/id_rsa", root), /outside the project directory/);import { CLI } from "../../src/constants.js";import { resolveCommandForExecution } from "../../src/utils/commandExecutor.js";import { UnifiedTool } from '../../src/tools/registry.js';import { ToolArguments } from '../../src/constants.js';import { processChangeModeOutput } from "../../src/utils/geminiExecutor.js";@modelcontextprotocol/sdk, chalk, d3-shape, prismjs, zod, zod-to-json-schema, @types/node, mermaid
curl -fsSL https://antigravity.google/cli/install.sh | bash # macOS / Linux
Gates applied: no_behavioural_pass.
40c3845fea8afull audit observations/trust-audit/mcp-server/jamubc__gemini-cli-3.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 |
|---|---|---|---|---|---|
| 2026-09-23 | 40c3845fea8a | CAUTION | B | 89 | source changed, verdict held |
Questions
What is the Gemini CLI MCP server?
MCP server that enables AI assistants to interact with Google Gemini CLI, leveraging Gemini's massive token window for large file analysis and codebase understanding
What tools does Gemini CLI expose?
9 in total: 9 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Gemini CLI safe to connect to an agent?
With care. The audit graded it B (89/100) and found 9 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Gemini CLI need?
It reads DEEPSEEK_API_KEY and OPENROUTER_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 does Gemini CLI run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as gemini-mcp-tool at 1.1.8.
How current is this page?
The grade is for one exact copy of the source (40c3845fea8a), read on 2026-09-23. The repository is watched and re-audited when it changes.