Mcp Client Typescript
About
The MCP Docs Server is a Node.js implementation of a Model Context Protocol (MCP) server that provides a powerful tool to search and retrieve up-to-date documentation snippets from popular AI/ML libraries. It leverages the Serper API to perform Google searches restricted to speci
Details
- Author
- anasyakubu
- Downloads
- 306
- Categories
- Knowledge Base
Jump to
- MCP-compliant server using @modelcontextprotocol/sdk
- get_docs tool for searching documentation
- Supports LangChain, LlamaIndex, and OpenAI
- Returns plain text from documentation pages
- Handles timeouts and search failures gracefully
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Mcp Client TypescriptCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Clone the repository, install dependencies with npm install, create a .env file with your SERPER_API_KEY, and run node server.js. From a compatible MCP client, invoke node client.js path/to/server.js to use the exposed get_docs tool.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp client typescript": {
"mcp-client-typescript": {
"command": "node",
"args": [
"server.js"
]
}
}
}
}McpServers
{
"mcp-client-typescript": {
"command": "node",
"args": [
"server.js"
]
}
}# MCP Docs Server
This project implements a Model Context Protocol (MCP) server in Node.js that provides a tool to search and fetch documentation snippets for popular AI/ML libraries.
---
🚀 Features
✅ MCP-compliant server (using @modelcontextprotocol/sdk)
✅ Tool: get_docs
✅ Searches Google for latest docs using Serper API
✅ Supports:
- LangChain
- LlamaIndex
- OpenAI
✅ Returns plain text from documentation pages
✅ Handles timeouts and search failures gracefully
---
📁 Project Structure
mcp-docs-server/
├── server.js # The MCP server implementation
├── .env # Environment variables
└── README.md # This file
---
⚙️ Setup
1. Clone the repository
bash
git clone <repo-url>
cd mcp-docs-server
2. Install dependencies
npm install
3. Create a .env file
SERPER_API_KEY=your_serper_api_key
4. Run the MCP server
node server.js
---
🛠️ Usage
The server exposes one tool:
get\_docs
Description:
Searches the latest documentation for a given query and library.
Arguments:
query (string): e.g. "Chroma DB"
library (string): one of "langchain", "llama-index", "openai"
Returns:
Plain text content fetched from the search results.
Example usage from a compatible MCP client:
node client.js path/to/server.js
---
📦 Dependencies
@modelcontextprotocol/sdk
dotenv
httpx
jsdom
---
📝 Notes
The MCP server uses the Serper API for Google search.
To get a Serper API key, visit serper.dev.
---
🤝 Contributing
Feel free to open issues or submit pull requests!
---
📄 License
MIT License.
---
🔗 Links
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
