youdotcom MCP

Local 2025-09-01 01:05:20 0

MCP server that provides Claude AI assistants with the ability to search the web, get news, and perform research using the You.com API.

This MCP (Model Context Protocol) server provides AI assistants with the ability to search the web, get news, and perform research using the You.com API. Feedback welcomed.

Features

Web Search: Access to You.com s web search functionality
Smart Search: AI-powered answers with citation support
Research: Comprehensive, citation-backed answers for academic queries
News Search: Latest news articles on any topic

Prerequisites

Node.js (v16 or higher)
npm or yarn
You.com API key (get one from api.you.com)

Installation

Clone this repository:

git clone https://github.com/jimbul/youcom-mcp.git
cd youcom-mcp

Install dependencies:
```
npm install
```
Create a .env file based on the example:
```
cp .env.example .env
```
Add your You.com API key to the .env file:
```
YOU_API_KEY=your_actual_api_key_here
```
Build the project:
```
npm run build
```

Running Locally (Optional)

You can run the server locally for testing:

npm start

Setting up with Claude

To use this MCP server with Claude (Anthropic Assistant), you need to configure Claude to use this server:

Open the Claude extension settings in VS Code:
Click on the Claude icon in the VS Code sidebar
Click on the settings icon (⚙️) and select "MCP Settings"
Add the following configuration to the mcpServers section:

"youcom-mcp": {
  "autoApprove": [],
  "disabled": false,
  "command": "node",
  "args": [
    "/absolute/path/to/your/youcom-mcp/dist/index.js"
  ],
  "env": {
    "YOU_API_KEY": "your_actual_api_key_here"
  },
  "transportType": "stdio"
}

Important Notes: - Replace /absolute/path/to/your/youcom-mcp/dist/index.js with the actual path on your system - Replace your_actual_api_key_here with your You.com API key

Usage Examples

Once configured, you can use the MCP tools directly in your conversations with Claude:

Web Search

<use_mcp_tool>
<server_name>youcom-mcp</server_name>
<tool_name>web_search</tool_name>
<arguments>
{
  "query": "latest research on renewable energy"
}
</arguments>
</use_mcp_tool>

Smart Search

<use_mcp_tool>
<server_name>youcom-mcp</server_name>
<tool_name>smart_search</tool_name>
<arguments>
{
  "query": "how do quantum computers work",
  "instructions": "explain in simple terms"
}
</arguments>
</use_mcp_tool>

Research

<use_mcp_tool>
<server_name>youcom-mcp</server_name>
<tool_name>research</tool_name>
<arguments>
{
  "query": "effects of climate change on ocean ecosystems",
  "instructions": "focus on coral reefs"
}
</arguments>
</use_mcp_tool>

News Search

<use_mcp_tool>
<server_name>youcom-mcp</server_name>
<tool_name>news_search</tool_name>
<arguments>
{
  "query": "latest developments in AI"
}
</arguments>
</use_mcp_tool>

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Running evals

The evals package loads an mcp client that then runs the index.ts file, so there is no need to rebuild between tests. You can load environment variables by prefixing the npx command. Full documentation can be found here.

OPENAI_API_KEY=your-key  npx mcp-eval src/evals/evals.ts src/index.ts

License

MIT

Acknowledgements

This project uses the You.com API for search functionality.

[
  {
    "inputSchema": {
      "$schema": "http://json-schema.org/draft-07/schema#",
      "additionalProperties": false,
      "properties": {
        "query": {
          "description": "The search query to send to You.com",
          "type": "string"
        }
      },
      "required": [
        "query"
      ],
      "type": "object"
    },
    "name": "web_search"
  },
  {
    "inputSchema": {
      "$schema": "http://json-schema.org/draft-07/schema#",
      "additionalProperties": false,
      "properties": {
        "conversationId": {
          "description": "A hex UUID to maintain conversation continuity (optional)",
          "type": "string"
        },
        "instructions": {
          "description": "Custom instructions for tailoring the response (optional)",
          "type": "string"
        },
        "query": {
          "description": "The query to send to You.com s Smart API",
          "type": "string"
        }
      },
      "required": [
        "query"
      ],
      "type": "object"
    },
    "name": "smart_search"
  },
  {
    "inputSchema": {
      "$schema": "http://json-schema.org/draft-07/schema#",
      "additionalProperties": false,
      "properties": {
        "instructions": {
          "description": "Custom instructions for tailoring the response (optional)",
          "type": "string"
        },
        "query": {
          "description": "The research query to send to You.com s Research API",
          "type": "string"
        }
      },
      "required": [
        "query"
      ],
      "type": "object"
    },
    "name": "research"
  },
  {
    "inputSchema": {
      "$schema": "http://json-schema.org/draft-07/schema#",
      "additionalProperties": false,
      "properties": {
        "query": {
          "description": "The news query to send to You.com s News API",
          "type": "string"
        }
      },
      "required": [
        "query"
      ],
      "type": "object"
    },
    "name": "news_search"
  }
]