What is Opendeepsearch Mcp

OpenDeepSearch MCP is a Model Context Protocol (MCP) server designed for OpenDeepSearch, enabling large language model (LLM) applications to leverage its search capabilities.

Use cases

Use cases include enhancing LLM applications with web search capabilities, integrating search functions into AI-driven chatbots, and providing contextual information retrieval in various applications.

How to use

To use OpenDeepSearch MCP, install the ‘uv’ dependency manager, sync the necessary dependencies in the ‘mcp_server’ directory, and configure the required environment variables, especially API keys for LLM providers.

Key features

Key features include exposing OpenDeepSearch’s search functionality as MCP tools, integration with Claude Desktop and other MCP-compatible clients, and providing a standardized interface for LLM applications to access web search capabilities.

Where to use

OpenDeepSearch MCP can be used in various fields such as AI research, natural language processing, and applications requiring advanced search functionalities.

OpenDeepSearch MCP Server

This is a Model Context Protocol (MCP) server for OpenDeepSearch that allows LLM applications to interact with OpenDeepSearch’s search capabilities.

Features

• Exposes OpenDeepSearch’s search functionality as MCP tools
• Integrates with Claude Desktop and other MCP-compatible clients
• Provides a standardized interface for LLM applications to access web search capabilities

Setup

This project uses uv for dependency management.

1. Install uv: Follow the instructions here.
2. Sync Dependencies: Navigate to the mcp_server directory and run:

   uv sync
   

   This will install dependencies based on pyproject.toml and uv.lock.

Configuration

The server requires certain environment variables to function correctly, especially API keys for the underlying services. These can be set directly in your environment or passed via the MCP client configuration (e.g., using Smithery CLI).

Note: API keys passed directly as arguments to the perform_search tool (serper_api_key, searxng_api_key, jina_api_key) will temporarily override the environment variables for that specific call.

Usage with Smithery CLI

You can run this server using the Smithery CLI and the provided smithery.yaml configuration file. This allows you to easily manage the required environment variables.

# Example: Run with OpenRouter key and Serper key
npx -y @smithery/cli@latest run . --config '{"openrouterApiKey":"sk-or-...", "serperApiKey":"your-serper-key"}'

# Example: Run with OpenAI key and SearXNG
npx -y @smithery/cli@latest run . --config '{"openaiApiKey":"sk-...", "searxngInstanceUrl":"https://your-searxng-instance.com"}'

# Example: Run with Gemini key
npx -y @smithery/cli@latest run . --config '{"geminiApiKey":"..."}'

# Example: Run with Azure keys
npx -y @smithery/cli@latest run . --config '{"azureApiKey":"...", "azureApiBase":"https://your-azure.openai.azure.com/", "azureApiVersion":"2024-02-01", "azureDeploymentId":"your-deployment"}'

The smithery.yaml file defines the necessary configuration schema. Refer to it for all available options.

Development

This package follows the MCP specification and provides tools for search functionality through OpenDeepSearch.