Language-based search MCP server for semantic search and document reranking
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"langsearch-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# 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
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.