LangSearch

Provides access to LangSearch Web Search and Semantic Rerank APIs via MCP for AI assistants.
  • typescript

0

GitHub Stars

typescript

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "ojamals-langsearch-mcp-ts": {
      "command": "node",
      "args": [
        "/absolute/path/to/langsearch-mcp-ts/dist/index.js"
      ],
      "env": {
        "LANGSEARCH_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You deploy an MCP server that exposes LangSearch web search and semantic reranking capabilities to your AI assistants. With this server you can perform web searches and semantically rerank results to suit your query, all integrated through MCP tooling for seamless conversations.

How to use

You integrate the LangSearch MCP server into your client workflow to access two main capabilities: web search with rich filtering and semantic reranking of documents. Use the web search tool to fetch results with options for freshness, summary inclusion, and result count. Use the semantic rerank tool to reorder a list of documents by how closely they semantically match your query, receiving relevance scores alongside the re-ordered results.

How to install

Prerequisites: Node.js installed on your system. You also need an active LangSearch API key to access the services.

# Step 1: Install dependencies
npm install

# Step 2: Build the project
npm run build

# Step 3: Prepare environment
cp .env.example .env

Configuration and usage notes

Configure your environment with your LangSearch API key to enable authentication with LangSearch services.

LANGSEARCH_API_KEY=your-api-key-here

Additional setup for Claude Desktop integration

If you use Claude Desktop, add the LangSearch MCP server configuration to your Claude desktop configuration file to enable tools in conversations.

{
  "mcpServers": {
    "langsearch": {
      "command": "node",
      "args": [
        "/absolute/path/to/langsearch-mcp-ts/dist/index.js"
      ],
      "env": {
        "LANGSEARCH_API_KEY": "your-api-key-here"
      }
    }
  }
}

Standalone mode and development tips

Development mode can run with auto-reload, and production mode builds the project and starts the server for long-running use.

# Development mode with auto-reload
npm run dev

# Production mode
npm run build
npm start

Testing the server

You can verify functionality using MCP inspection tooling. Run the inspector and connect via the stdio transport to your local server to validate tool names, parameters, and responses.

npm run inspector

Available tools

langsearch_web_search

Search the web using LangSearch's Web Search API with options for freshness, summaries, and result count.

langsearch_semantic_rerank

Rerank a list of documents by semantic relevance to a query and return scores.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational