🔍 Gemini LLM-powered MCP Client integrated with Web Search Remote MCP Server
A local web search system that combines Google's Gemini LLM with a FastMCP tool-calling interface and a Streamlit UI. Uses SerpApi for live, real-time search results via a custom MCP server to show Remote MCP Server capabilities with Gemini LLM.
Features
- ✅ Google's Gemini API integration with Remote FastMCP Server
- ✅ Tool calling using FastMCP based Remote MCP Server
- ✅ Custom MCP Server with live web search via SerpApi
MCP Official Doc
Installation
-
Clone the repository:
git clone https://github.com/genieincodebottle/generative-ai.git cd genai-usecases\mcp\web_search_mcp
-
Open the Project in VS Code or any code editor.
-
Create a virtual environment:
pip install uv #if uv not installed uv venv .venv\Scripts\activate # On Linux -> source venv/bin/activate
-
Create a requirements.txt file and add the following libraries:
asyncio>=3.4.3 aiohttp>=3.12.13 python-dotenv>=1.1.0 google-search-results>=2.4.2 fastmcp>=2.8.1 mcp>=1.9.4 streamlit>=1.45.1 requests>=2.32.4 google-genai>=1.20.0 anthropic>=0.54.0 openai>=1.88.0
-
Install dependencies:
uv pip install -r requirements.txt
-
Set up environment variables
- Rename .env.example to .env
- Update the file with your API keys:
GOOGLE_API_KEY=your_key_here # Using the free-tier API SERPAPI_API_KEY=your_serpapi_key # Using free-tier
-
🔑 Get your API keys:
For GOOGLE_API_KEY follow this -> https://aistudio.google.com/app/apikey
For SERPAPI_API_KEY follow this -> https://serpapi.com/manage-api-key
-
Run the MCP Server at one terminal
cd genai-usecases\mcp\web_search_mcp .venv\Scripts\activate python web_search_mcp_server.py --host localhost --port 8000
-
Run the Streamlit Client App in another terminal (Split VSCode terminal or Open window's terminal)
cd genai-usecases\mcp\web_search_mcp .venv\Scripts\activate streamlit run gemini_mcp_client.py
-
Once started, go to:
http://localhost:8501
Use the sidebar to view Gemini API status, adjust model/temperature, and run queries with real-time web search using SerpApi.
⚙️ How It Works
- The Remote MCP server exposes tools (like web_search) via FastMCP over Streamable HTTP.
- The Streamlit app uses Gemini's function calling to request results from the Remote Web Saerch MCP server.
- Gemini combines LLM reasoning with live data via SerpApi using tool calling.
Metadata
Release files for iflow-mcp_genieincodebottle-web-search-mcp 2025.2.7.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| iflow_mcp_genieincodebottle_web_search_mcp-2025.2.7.0.tar.gz | 5.1 kB | Without provenance | Details for iflow_mcp_genieincodebottle_web_search_mcp-2025.2.7.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| iflow_mcp_genieincodebottle_web_search_mcp-2025.2.7.0-py3-none-any.whl | Python 3 | none | any | Details for iflow_mcp_genieincodebottle_web_search_mcp-2025.2.7.0-py3-none-any.whl |
Total release size: 11.4 kB
Release files / iflow_mcp_genieincodebottle_web_search_mcp-2025.2.7.0.tar.gz
| Download URL | iflow_mcp_genieincodebottle_web_search_mcp-2025.2.7.0.tar.gz |
|---|---|
| Size | 5.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
afa4f08a8649feeb7280a079dcd4903990fe0789a6b45b6ce85bc6196295ad28
|
|
BLAKE2b-256 checksum How to use checksums |
e64a822734a9f8d681fe30254de9e8462c63361ef330d12297a8d81cf8dfcdd7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.0 {"installer":{"name":"uv","version":"0.10.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / iflow_mcp_genieincodebottle_web_search_mcp-2025.2.7.0-py3-none-any.whl
| Download URL | iflow_mcp_genieincodebottle_web_search_mcp-2025.2.7.0-py3-none-any.whl |
|---|---|
| Size | 6.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ecbcb57a394805ac0266381afb31b7f15faec68a9f3a7315b448121562bd044b
|
|
BLAKE2b-256 checksum How to use checksums |
f142e6e9b519cc4da24d2bedbe9332075b30422b6d864d434d62a8b77c16ac4e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.0 {"installer":{"name":"uv","version":"0.10.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for iflow-mcp_genieincodebottle-web-search-mcp 2025.2.7.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.