Ollama MCP Bridge WebUI
O

Ollama MCP Bridge WebUI

一个连接本地LLM与MCP服务器的TypeScript桥梁项目,提供Web界面使开源模型能使用类似Claude的工具能力,支持文件系统、网络搜索和复杂推理等功能。
2.5分
6.4K

What is Ollama-MCP Bridge?

The Ollama-MCP Bridge is a TypeScript application that connects locally running language models (through Ollama) with various Model Context Protocol (MCP) servers. It provides a web interface that allows you to interact with open-source AI models while giving them access to powerful tools like filesystem operations, web search, and reasoning capabilities - similar to what commercial AI assistants offer.

How to use the Bridge?

After installation, you can access the web interface where you can chat with your local AI model. The system will automatically determine when to use tools like file access or web search based on your questions. You don't need to manually select tools - the AI will handle this intelligently.

Use Cases

Ideal for: 1) Privacy-conscious users who want AI assistance without cloud services, 2) Developers needing local AI with tool access, 3) Researchers experimenting with open-source models, 4) Anyone wanting to extend local AI capabilities with web search and file access.

Key Features

Multi-MCP Integration
Connect and use multiple MCP servers simultaneously for different capabilities
Automatic Tool Detection
The system intelligently selects the right tool based on your queries without manual intervention
Web Interface
Clean, user-friendly interface with collapsible tool descriptions and conversation history
Comprehensive Toolset
Includes filesystem access, web search (via Brave), and advanced reasoning capabilities
Local Operation
Runs entirely on your hardware with optional internet connectivity only for web searches
Advantages
Privacy: Your data stays on your local machine
Flexibility: Combine different tools as needed
Cost-effective: No API fees for local model use
Customizable: Adjust configuration to your needs
Offline capable: Most features work without internet
Limitations
Requires decent hardware to run local models effectively
Web search requires a Brave API key (free tier available)
Local models may be less capable than commercial cloud options
Initial setup requires some technical knowledge

Getting Started

Automatic Installation
Run the automatic installation script for easiest setup
Manual Setup
If you prefer manual control, follow these steps:
Configuration
Edit the bridge_config.json and .env files to customize your setup
Running the Bridge
Start the bridge and access the web interface

Example Uses

Research Assistance
Find and summarize recent information on a topic
File Management
Work with local files through natural language
Complex Problem Solving
Break down multi-step problems

Frequently Asked Questions

What models are supported?
Do I need programming knowledge to use this?
How do I get a Brave API key?
Can I add my own tools?
Where are files stored?

Additional Resources

Ollama Documentation
Official documentation for Ollama
Model Context Protocol
MCP GitHub repository
Brave Search API
Sign up for Brave Search API keys
Qwen Model Info
Details about the Qwen language models

安装

复制以下命令到你的Client进行配置
{
  "mcpServers": {
    "filesystem": {
      "command": "node",
      "args": [
        "To/Your/Directory/Ollama-MCP-Bridge-WebUI/node_modules/@modelcontextprotocol/server-filesystem/dist/index.js",
        "To/Your/Directory/Ollama-MCP-Bridge-WebUI/../workspace"
      ],
      "allowedDirectory": "To/Your/Directory/Ollama-MCP-Bridge-WebUI/../workspace"
    },
    "brave-search": {
      "command": "node",
      "args": [
        "To/Your/Directory/Ollama-MCP-Bridge-WebUI/node_modules/@modelcontextprotocol/server-brave-search/dist/index.js"
      ],
      "env": {
        "BRAVE_API_KEY": "$BRAVE_API_KEY"
      }
    },
    "sequential-thinking": {
      "command": "node",
      "args": [
        "To/Your/Directory/Ollama-MCP-Bridge-WebUI/node_modules/@modelcontextprotocol/server-sequential-thinking/dist/index.js"
      ]
    }
  },
  "llm": {
    "model": "qwen2.5-coder:7b-instruct-q4_K_M",
    "baseUrl": "http://localhost:11434",
    "apiKey": "ollama",
    "temperature": 0.7,
    "maxTokens": 8000
  },
  "systemPrompt": "You are a helpful assistant that can use various tools to help answer questions. You have access to three main tool groups: 1) Filesystem operations - for working with files and directories, 2) Brave search - for finding information on the web, 3) Sequential thinking for complex problem-solving. When a user asks a question that requires external information, real-time data, or file manipulation, you should use a tool rather than guessing or using only your pre-trained knowledge."
}
注意:您的密钥属于敏感信息,请勿与任何人分享。

替代品

F
Flux GitOps
Flux Operator是一个Kubernetes CRD控制器,用于管理CNCF Flux CD的生命周期,提供自动化安装、配置、升级功能,支持多租户锁定、分片、水平扩展等高级配置,并集成自服务环境和AI辅助GitOps功能。
Go
5.3K
4分
N
Notte Browser
已认证
Notte是一个开源的全栈网络AI代理框架,提供浏览器会话、自动化LLM驱动的代理、网页观察与操作、凭证管理等功能,旨在将互联网转化为代理友好的环境,并通过自然语言描述网站结构,降低LLM的认知负担。
15.5K
4.5分
S
Search1api
Search1API MCP Server是一个基于Model Context Protocol (MCP)的服务器,提供搜索和爬取功能,支持多种搜索服务和工具。
TypeScript
14.0K
4分
D
Duckduckgo MCP Server
已认证
DuckDuckGo搜索MCP服务器,为Claude等LLM提供网页搜索和内容抓取服务
Python
28.9K
4.3分
B
Bing Search MCP
一个用于集成微软Bing搜索API的MCP服务器,支持网页、新闻和图片搜索功能,为AI助手提供网络搜索能力。
Python
14.3K
4分
M
MCP Alchemy
已认证
MCP Alchemy是一个连接Claude Desktop与多种数据库的工具,支持SQL查询、数据库结构分析和数据报告生成。
Python
12.8K
4.2分
P
Postgresql MCP
一个基于FastMCP库的PostgreSQL数据库MCP服务,提供对指定表的CRUD操作、模式检查和自定义SQL查询功能。
Python
9.9K
4分
A
Agentic Radar
Agentic Radar是一个用于分析和评估代理系统的安全扫描工具,帮助开发者、研究人员和安全专家理解代理系统的工作流程并识别潜在漏洞。
Python
10.8K
5分
F
Firecrawl MCP Server
Firecrawl MCP Server是一个集成Firecrawl网页抓取能力的模型上下文协议服务器,提供丰富的网页抓取、搜索和内容提取功能。
TypeScript
43.9K
5分
F
Figma Context MCP
Framelink Figma MCP Server是一个为AI编程工具(如Cursor)提供Figma设计数据访问的服务器,通过简化Figma API响应,帮助AI更准确地实现设计到代码的一键转换。
TypeScript
32.5K
4.5分
D
Duckduckgo MCP Server
已认证
DuckDuckGo搜索MCP服务器,为Claude等LLM提供网页搜索和内容抓取服务
Python
28.9K
4.3分
M
Minimax MCP Server
MiniMax Model Context Protocol (MCP) 是一个官方服务器,支持与强大的文本转语音、视频/图像生成API交互,适用于多种客户端工具如Claude Desktop、Cursor等。
Python
23.3K
4.8分
E
Exa Web Search
已认证
Exa MCP Server是一个为AI助手(如Claude)提供网络搜索功能的服务器,通过Exa AI搜索API实现实时、安全的网络信息获取。
TypeScript
21.2K
5分
E
Edgeone Pages MCP Server
EdgeOne Pages MCP是一个通过MCP协议快速部署HTML内容到EdgeOne Pages并获取公开URL的服务
TypeScript
15.0K
4.8分
C
Context7
Context7 MCP是一个为AI编程助手提供实时、版本特定文档和代码示例的服务,通过Model Context Protocol直接集成到提示中,解决LLM使用过时信息的问题。
TypeScript
27.4K
4.7分
B
Baidu Map
已认证
百度地图MCP Server是国内首个兼容MCP协议的地图服务,提供地理编码、路线规划等10个标准化API接口,支持Python和Typescript快速接入,赋能智能体实现地图相关功能。
Python
21.1K
4.5分
AIBase
智启未来,您的人工智能解决方案智库