Stateless MCP server that proxies research queries to Gemini CLI, reducing agent context/model usage
Connect Gemini to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Stateless MCP server that proxies research queries to Gemini CLI, reducing agent context/model usage. The gemini mcp server is what makes that connection.
A lightweight, stateless MCP (Model Context Protocol) server that lets developer agents (Claude Code, GitHub Copilot) hand off deep repository analysis to the Gemini CLI. The server is read-only, returns structured JSON (as text content), and is designed to reduce the calling agent's context and model usage.
Gemini Researcher accepts queries from your AI agent and uses Gemini CLI to analyze your local code files. Results are returned as formatted JSON for your agent to use.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
quick_query — flash -> flash_lite -> autodeep_research — pro -> flash -> flash_lite -> autoanalyze_directory — flash -> flash_lite -> autovalidate_paths — Pre-check file pathshealth_check — Diagnosticsfetch_chunk — Get chunked responsesConfiguration is passed through the environment: PROJECT_ROOT, GEMINI_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
npm install -g @google/gemini-cli - Gemini CLI authenticated (recommended: gemini → Login with Google) or set GEMINI_API_KEY Quick checks:Installation goes through your MCP client rather than a global install: point it at gemini-researcher on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Gemini's toolset — quick_query, deep_research, analyze_directory and 3 more — is a fair guide to whether it matches your workflow. It is maintained by capyBearista; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Gemini's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| quick_query | flash -> flash_lite -> auto |
| deep_research | pro -> flash -> flash_lite -> auto |
| analyze_directory | flash -> flash_lite -> auto |
| validate_paths | Pre-check file paths |
| health_check | Diagnostics |
| fetch_chunk | Get chunked responses |
{
"mcpServers": {
"gemini-researcher": {
"command": "npx",
"args": ["-y", "gemini-researcher"],
"env": {
"PROJECT_ROOT": "your-value",
"GEMINI_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
npm install -g @google/gemini-cli - Gemini CLI authenticated (recommended: gemini → Login with Google) or set GEMINI_API_KEY Quick checks:| Variable | Description | Required |
|---|---|---|
| PROJECT_ROOT | Configuration value read at startup. | Optional |
| GEMINI_API_KEY | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.