gem_searchLABSCO SUMMARY
Four tools shaped by the job, not by the model list.
You ask for search, reasoning, processing or file analysis, and the server picks the Gemini variant to run it on — which matters mostly for cost, since gem_process routes to the cheapest variant and gem_reason to the one that shows its work. The uniform file_path parameter is the other reason to reach for it: the same call handles a PDF, a source file or an image.
What it is
A Gemini API server with four task-shaped tools. Each one maps to the Gemini variant suited to it — grounded search, step-by-step reasoning, or cheap bulk processing — and every tool accepts a file_path so documents, code and images go in the same way.
What you get
- gem_search — factual questions answered with Gemini's search integration, so the response is grounded rather than recalled
- gem_reason — step-by-step reasoning for maths, science and code problems, with show_steps to see the working
- gem_process — the token-cheapest path, for summarising and extracting from text or files at volume
- gem_analyze — file analysis with the model picked automatically from the file type: images, code, or plain text
- A file_path parameter on every tool, with the MIME type detected for you
- Retries with exponential backoff when the API rate-limits you
Requirements
A Gemini API key from Google AI Studio, supplied as GEMINI_API_KEY in the environment or a .env file. Node.js 16 or newer. Install through the Smithery CLI, or clone, npm install and npm run build.
Setup effort
One command plus a key — npx -y @smithery/cli@latest install @PV-Bhat/gemsuite-mcp --client claude, then supply credentials
USE CASES
01
Answering a question that needs current facts
Ask with search grounding turned on instead of relying on the model's recall.
02
Getting a hard problem worked through
Hand over the problem, optionally with a file, and ask for the reasoning steps to be shown.
03
Summarising a long document cheaply
Point at the file and ask for a summary or a targeted extraction on the low-cost path.
04
Reviewing a file you cannot read yourself
Send an image, a PDF or a source file with an instruction and let the model be chosen from the file type.
4 tools
Listed in project docs. Your client may show a different list.
gem_reasongem_processgem_analyzeBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation. Older guides use gemini_process, gemini_reason, gemini_search and gemini_analyze; those names no longer exist.
Requires
GEMINI_API_KEY in your environment
INSTALLATION
Connect your client
Server setup
Build from source
TERMINAL
# Clone the repository
git clone https://github.com/PV-Bhat/gemsuite-mcp.git
cd gemsuite-mcp
# Install dependencies
npm install
# Set your Gemini API key
echo "GEMINI_API_KEY=<YOUR_GEMINI_API_KEY>" > .env
# Build the project
npm run build
# Start the server
npm startnpx
Claude Desktop
TERMINAL
npx -y @smithery/cli@latest install @PV-Bhat/gemsuite-mcp --client claude
