ollama-websearch-mcp

ollama-websearch-mcp

Enables performing web searches and fetching web page content via Ollama's hosted APIs, providing search results and raw page data.

Category
访问服务器

README

Ollama WebSearch MCP Server

MCP server for Ollama web search and web fetch APIs.

Overview

This MCP server exposes two tools for interacting with Ollama's web services:

  • web_search: Perform a web search using Ollama's hosted search API
  • web_fetch: Fetch the content of a web page

Requirements

  • Python 3.10+
  • Ollama account (for cloud API access)

Installation

Clone

git clone https://github.com/akopper/ollama-websearch-mcp.git
cd ollama-websearch-mcp

From Source

pip install -e .

With uvx

uvx runs the server in stdio mode by default (for Claude Desktop/Cursor):

uvx --from https://github.com/akopper/ollama-websearch-mcp ollama-websearch-mcp

For HTTP mode with uvx:

uvx --from https://github.com/akopper/ollama-websearch-mcp ollama-websearch-mcp -- --http

Docker

The Docker image defaults to HTTP mode.

# HTTP mode (default) - for remote usage
docker run -d -p 8000:8000 -e OLLAMA_API_KEY=your-api-key ghcr.io/akopper/ollama-websearch-mcp

# stdio mode - for Claude Desktop/Cursor
docker run -it --rm -e OLLAMA_API_KEY=your-api-key ghcr.io/akopper/ollama-websearch-mcp --stdio

Docker Compose

cp .env.example .env
# Edit .env with your API key
docker-compose up -d

Configuration

Environment Variables

Variable Description Default
OLLAMA_API_KEY API key for Ollama cloud services None
OLLAMA_HOST Host URL for Ollama https://ollama.com

Getting an API Key

  1. Go to ollama.com
  2. Sign in to your account
  3. Navigate to API settings
  4. Generate an API key

Usage

Running the Server

stdio mode (default, for Claude Desktop/Cursor)

# Using the installed command
ollama-websearch-mcp

# Or directly with Python
python -m ollama_websearch_mcp.server

HTTP mode (for remote usage)

python -m ollama_websearch_mcp.server --http

The server will start on http://localhost:8000/mcp by default.

Claude Desktop Integration

Add the following to your Claude Desktop configuration:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "ollama-websearch": {
      "command": "ollama-websearch-mcp",
      "env": {
        "OLLAMA_API_KEY": "your-api-key-here"
      }
    }
  }
}

Or with a custom Python environment:

{
  "mcpServers": {
    "ollama-websearch": {
      "command": "/path/to/venv/bin/python",
      "args": ["-m", "ollama_websearch_mcp.server"],
      "env": {
        "OLLAMA_API_KEY": "your-api-key-here"
      }
    }
  }
}

Cursor Integration

Add to Cursor settings (or .cursor/mcp.json in project):

{
  "mcpServers": {
    "ollama-websearch": {
      "command": "ollama-websearch-mcp",
      "env": {
        "OLLAMA_API_KEY": "your-api-key-here"
      }
    }
  }
}

MCPorter Integration

MCPorter can discover and use this MCP server. Create a config file:

// config/mcporter.json
{
  "mcpServers": {
    "ollama-websearch": {
      "description": "Ollama web search and web fetch MCP server",
      "command": "ollama-websearch-mcp",
      "env": {
        "OLLAMA_API_KEY": "$env:OLLAMA_API_KEY"
      }
    }
  }
}

Or run ad-hoc:

# List tools
npx mcporter list ollama-websearch

# Call a tool
npx mcporter call ollama-websearch.web_search query:python max_results:10

Available Tools

web_search

Perform a web search using Ollama's hosted search API.

Parameters:

  • query (required): The search query string
  • max_results (optional): Maximum number of results to return (default: 10)

Returns: Dictionary containing search results with title, url, and snippet.

web_fetch

Fetch the content of a web page.

Parameters:

  • url (required): The absolute URL to fetch

Returns: Dictionary containing the fetched content with html, text, and metadata.

Development

Setup

# Create virtual environment
python -m venv .venv
source .venv/bin/activate

# Install with dev dependencies
pip install -e ".[dev]"

Running Tests

# Run all tests
pytest

# Run a single test
pytest tests/test_server.py::TestWebSearch::test_web_search_returns_dict

# Run with verbose output
pytest -v

# Run with coverage
pytest --cov=src --cov-report=html

Linting

# Check code style
ruff check src/ tests/

# Auto-fix issues
ruff check src/ tests/ --fix

Running the Server for Development

# stdio mode with mcp dev
mcp dev src/ollama_websearch_mcp/server.py

# Or run directly
python -m ollama_websearch_mcp.server

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选