MCP.so
登录

AIO-MCP Server

@athapong

基本信息

分类

版本控制

传输方式

stdio

作者

athapong

关于 AIO-MCP Server

🚀 All-in-one MCP server with AI search, RAG, and multi-service integrations (GitLab/Jira/Confluence/YouTube) for AI-enhanced development workflows. Folk from https://github.com/nguyenvanduocit/all-in-one-model-context-protocol

AIO-MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "aio-mcp": {
      "command": "<path>/<to>/aio-mcp",
      "env": {
        "ENABLE_TOOLS": "",
        "QDRANT_HOST": "",
        "QDRANT_PORT": "",
        "QDRANT_API_KEY": "",
        "ATLASSIAN_HOST": "",
        "ATLASSIAN_EMAIL": "",
        "ATLASSIAN_TOKEN": "",
        "GITLAB_HOST": "https://gitlab.com",
        "GITLAB_TOKEN": "glpat-",
        "BRAVE_API_KEY": "",
        "GOOGLE_AI_API_KEY": "",
        "PROXY_URL": "",
        "OPENAI_API_KEY": "",
        "OPENAI_BASE_URL": "",
        "OPENAI_EMBEDDING_MODEL": "",
        "GOOGLE_TOKEN_FILE": "<path>/<to>/google-token.json",
        "GOOGLE_CREDENTIALS_FILE": "<path>/<to>/google-credentials.json",
        "GOOGLE_MAPS_API_KEY": "",
        "DEEPSEEK_API_KEY": "",
        "USE_OLLAMA_DEEPSEEK": "",
        "USE_OPENROUTER": "",
        "OPENROUTER_API_KEY": ""
      }
    }
  }
}

AIO-MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is AIO-MCP Server?

AIO-MCP Server is a Model Context Protocol (MCP) server implementation with built-in integrations for GitLab, Jira, Confluence, YouTube, Google services (Calendar, Chat, Maps), Brave Search, Gemini, and Deepseek. It provides AI-powered search capabilities and utility tools for development workflows, targeting developers and teams using Claude Desktop or other MCP clients.

How to use AIO-MCP Server?

Install via go install github.com/athapong/aio-mcp@latest (requires Go 1.23.2+) or automatically via Smithery. Create a .env file with your API keys and tokens for the services you want to use. Configure Claude Desktop by adding the server to claude_desktop_config.json. The server runs in either stdio mode (default) or SSE mode (enable with -sse flag or ENABLE_SSE=true). Use the ENABLE_TOOLS environment variable as a comma-separated list of tool groups to enable (leave empty to enable all).

Key features of AIO-MCP Server

  • Integrates with GitLab, Jira, Confluence, YouTube, and more
  • Gemini-powered AI web search (ai_web_search)
  • Deepseek reasoning engine for multi-step problem solving
  • Google Calendar event creation, listing, updating, and responding
  • Google Chat space listing and message sending
  • Brave Search, fetch, and Google Maps tools
  • GitLab project, merge request, pipeline, commit, and file management
  • Confluence page search, create, update, and version comparison
  • Qdrant-based RAG tools and script execution tools

Use cases of AIO-MCP Server

  • Automate development workflows with GitLab, Jira, and Confluence integration
  • Perform AI‑powered web searches and deep reasoning tasks
  • Manage Google Calendar events and Google Chat messages from within an MCP client
  • Search and update Confluence knowledge bases using CQL
  • Enable or disable tool groups to tailor the server to specific projects

常见问题

1

What are the prerequisites to run AIO-MCP Server?

Go 1.23.2 or higher is required. You also need API keys and tokens for each service you intend to use (e.g., GitLab token, Atlassian token, Brave API key, Google AI API key, etc.).

2

How can I enable only specific tools?

Set the `ENABLE_TOOLS` environment variable to a comma-separated list of tool group names (e.g., `gitlab,confluence,jira`). If left empty or unset, all tools are enabled.

3

Does the server support SSE (Server‑Sent Events)?

Yes. You can enable SSE mode with the `-sse` command-line flag or by setting `ENABLE_SSE=true`, `SSE_ADDR`, and `SSE_BASE_PATH` in your `.env` file. SSE mode provides an HTTP endpoint for real-time communication.

4

Where does the data live?

The server acts as a bridge; it makes API calls to external services (GitLab, Confluence, Google, etc.) using your credentials. The server itself does not store data persistently beyond temporary in-memory state.

5

What transports and authentication methods are supported?

The server supports stdio (standard input/output) and SSE (HTTP) transport. Authentication is handled via environment variables or the `claude_desktop_config.json` `env` block, with API keys and tokens passed to the respective service endpoints.

评论

版本控制 分类下的更多 MCP 服务器