AIO
🚀 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
What is AIO?
AIO is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🚀 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...
🚀 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
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 🚀 All-in-one MCP server with AI search, RAG, and multi-servi
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx aioConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use AIO
AIO-MCP is an all-in-one MCP server written in Go that integrates AI-powered search, RAG (retrieval-augmented generation) memory via Qdrant, and a wide range of productivity services — GitLab, Jira, Confluence, YouTube, Gmail, Google Calendar, and Google Chat — into a single configurable MCP server. It exposes nine functional tool groups selectable via environment variables, allowing teams to enable only the integrations they need, from code review automation to Confluence knowledge base search to Deepseek-powered chain-of-thought reasoning. Development teams that use Atlassian tools alongside GitLab and want a single MCP server to cover their entire workflow will find AIO-MCP a practical unified solution.
Prerequisites
- Go 1.21+ installed (for building from source) OR npx/Smithery for prebuilt install
- API keys for the services you want to enable (GitLab token, Atlassian API token, Google credentials, Brave API key, OpenAI/Deepseek key, etc.)
- Qdrant vector database running locally or remotely (for RAG features)
- Claude Desktop or another MCP-compatible AI client
Install via Smithery (recommended)
The fastest way to install AIO-MCP is via the Smithery CLI, which handles the binary installation and basic configuration automatically.
npx -y @smithery/cli install @athapong/aio-mcp --client claudeAlternative: Install via Go
If you have Go installed, build and install the binary directly from source.
go install github.com/athapong/aio-mcp@latestCreate a .env file with your credentials
Copy or create a .env file with the environment variables for the tool groups you want to enable. Set ENABLE_TOOLS to a comma-separated list of tool group names.
ENABLE_TOOLS=gitlab,jira,confluence,brave_search,youtube
GITLAB_HOST=https://gitlab.com
GITLAB_TOKEN=your-gitlab-personal-access-token
ATLASSIAN_HOST=https://yourcompany.atlassian.net
[email protected]
ATLASSIAN_TOKEN=your-atlassian-api-token
BRAVE_API_KEY=your-brave-search-api-keyConfigure Claude Desktop
Add AIO-MCP to your claude_desktop_config.json with the environment variables for your enabled tool groups.
{
"mcpServers": {
"aio-mcp": {
"command": "aio-mcp",
"args": [],
"env": {
"ENABLE_TOOLS": "gitlab,jira,confluence,brave_search",
"GITLAB_HOST": "https://gitlab.com",
"GITLAB_TOKEN": "your-gitlab-token",
"ATLASSIAN_HOST": "https://yourcompany.atlassian.net",
"ATLASSIAN_EMAIL": "[email protected]",
"ATLASSIAN_TOKEN": "your-atlassian-api-token",
"BRAVE_API_KEY": "your-brave-api-key"
}
}
}
}Enable RAG memory with Qdrant (optional)
To use the RAG memory feature for indexing and retrieving context across conversations, start a Qdrant instance and add the Qdrant configuration alongside OpenAI credentials for embedding.
# Start Qdrant locally with Docker
docker run -p 6333:6333 qdrant/qdrant
# Add to .env
QDRANT_HOST=localhost
QDRANT_PORT=6333
OPENAI_API_KEY=your-openai-key
OPENAI_EMBEDDING_MODEL=text-embedding-3-smallAIO Examples
Client configuration
Claude Desktop configuration for AIO-MCP with GitLab, Jira, Confluence, and web search enabled.
{
"mcpServers": {
"aio-mcp": {
"command": "aio-mcp",
"args": [],
"env": {
"ENABLE_TOOLS": "gitlab,jira,confluence,brave_search,youtube",
"GITLAB_HOST": "https://gitlab.com",
"GITLAB_TOKEN": "your-gitlab-personal-access-token",
"ATLASSIAN_HOST": "https://yourcompany.atlassian.net",
"ATLASSIAN_EMAIL": "[email protected]",
"ATLASSIAN_TOKEN": "your-atlassian-api-token",
"BRAVE_API_KEY": "your-brave-search-api-key"
}
}
}
}Prompts to try
These prompts use the various tool groups available in AIO-MCP:
- "List open merge requests assigned to me in GitLab project myorg/myrepo"
- "Search Confluence for documentation about our deployment process"
- "Create a Jira issue in project BACKEND titled 'Fix authentication timeout'"
- "Search the web for best practices for Go error handling in 2025"
- "Get the transcript of YouTube video https://youtube.com/watch?v=example"
- "Find all Jira issues in sprint 42 that are still in progress"Troubleshooting AIO
Tool group not available after setting ENABLE_TOOLS
Verify the tool group name is spelled exactly as documented: `gemini`, `fetch`, `brave_search`, `google_maps`, `confluence`, `youtube`, `jira`, `gitlab`, or `script`. Tool groups are comma-separated with no spaces in the ENABLE_TOOLS value.
Atlassian tools return 401 Unauthorized
Ensure ATLASSIAN_TOKEN is an Atlassian API token (not your account password). Generate one at https://id.atlassian.com/manage-profile/security/api-tokens. ATLASSIAN_EMAIL must match the email on your Atlassian account exactly.
aio-mcp binary not found after go install
Ensure your Go bin directory is on your PATH. Run `export PATH=$PATH:$(go env GOPATH)/bin` and add it to your shell profile. Verify with `which aio-mcp` after reloading the shell.
Frequently Asked Questions about AIO
What is AIO?
AIO is a Model Context Protocol (MCP) server that 🚀 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 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install AIO?
Follow the installation instructions on the AIO GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with AIO?
AIO works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is AIO free to use?
Yes, AIO is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
AIO Alternatives — Similar Coding Agents Servers
Looking for alternatives to AIO? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up AIO in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use AIO?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.