Metadata-Version: 2.4
Name: langsearch-mcp
Version: 0.1.0
Summary: Language-based search MCP server for semantic search and document reranking
Project-URL: Repository, https://github.com/yourusername/langsearch-mcp
Author-email: Your Name <your.email@example.com>
License: MIT
Classifier: Development Status :: 4 - Beta
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.10
Requires-Dist: fastapi>=0.115.12
Requires-Dist: httpx>=0.28.1
Requires-Dist: mcp[cli]>=1.6.0
Requires-Dist: python-dotenv>=1.1.0
Description-Content-Type: text/markdown

# LangSearch MCP

A language-based search MCP server that provides semantic search and document reranking capabilities.

## Features

- Semantic web search
- Document reranking based on relevance
- Easy integration with MCP clients like Cherry Studio

## Installation

You can install the package using pip:

```bash
pip install langsearch-mcp
```

Or install from source:

```bash
git clone https://github.com/yourusername/langsearch-mcp
cd langsearch-mcp
pip install .
```

## Usage

### As a Command Line Tool

After installation, you can run the MCP server directly from the command line:

```bash
langsearch-mcp
```

### As an MCP Server

The server can be used with any MCP client, including Cherry Studio. The server provides the following endpoints:

- `web_search`: Perform semantic web search
- `rerank_documents`: Rerank documents based on relevance to a query

## Configuration

The server can be configured using environment variables:

- `PORT`: The port to run the server on (default: 8000)
- Add any other environment variables your server uses

## Development

To set up the development environment:

1. Clone the repository
2. Create a virtual environment: `python -m venv .venv`
3. Activate the virtual environment:
   - Windows: `.venv\Scripts\activate`
   - Unix/MacOS: `source .venv/bin/activate`
4. Install dependencies: `pip install -e ".[dev]"`

## License

MIT License
