AIO-MCP Server
About
🚀 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
Details
- Transport
- SSE
Explore
- 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
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
AIO-MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
- Go 1.23.2 or higher
- Various API keys and tokens for the services you want to use
To install AIO-MCP Server for Claude Desktop automatically via Smithery (will guide you through interactive CLI setup):
npx -y @smithery/cli install @athapong/aio-mcp --client claude
Note: Smithery will interactively prompt you for required configuration values and handle environment setup automatically
To set the go install command to install into the Go bin path, you need to ensure your Go environment variables are correctly configured. Here's how to do it:
1. First, ensure you have a properly set GOPATH environment variable, which by default is $HOME/go on Unix-like systems or %USERPROFILE%\go on Windows.
2. The go install command places binaries in $GOPATH/bin by default. Make sure this directory is in your system's PATH environment variable.
Here's how to set this up on different operating systems:
export GOPATH=$HOME/go
export PATH=$PATH:$GOPATH/bin
After adding these lines, reload your shell configuration:
bashsource ~/.bashrc # or ~/.zshrc
[Environment]::SetEnvironmentVariable("GOPATH", "$env:USERPROFILE\go", "User")
[Environment]::SetEnvironmentVariable("PATH", "$env:PATH;$env:USERPROFILE\go\bin", "User")
{
"mcpServers": {
"aio-mcp": {
"command": "aio-mcp",
"env": {
"ENABLE_TOOLS": "",
"OPENAI_BASE_URL": "",
"GOOGLE_AI_API_KEY": "",
"GITLAB_TOKEN": "",
"GITLAB_HOST": "",
"QDRANT_HOST": "",
"QDRANT_API_KEY": "",
"PROXY_URL": "",
"OPENAI_API_KEY": "",
"GOOGLE_TOKEN_FILE": "",
"GOOGLE_CREDENTIALS_FILE": "",
"ATLASSIAN_TOKEN": "",
"BRAVE_API_KEY": "",
"QDRANT_PORT": "",
"ATLASSIAN_HOST": "",
"ATLASSIAN_EMAIL": "",
"USE_OPENROUTER": "", // "true" if you want to use openrouter for AI to help with reasoning on tool_use_plan, default is false
"DEEPSEEK_API_KEY": "", // specify the deepseek api key if you want to use deepseek for AI to help with reasoning on tool_use_plan
"OPENROUTER_API_KEY": "", // specify the openrouter api key if you want to use openrouter for AI to help with reasoning on tool_use_plan
"DEEPSEEK_API_BASE": "", // specify the deepseek api key if you want to use deepseek for AI to help with reasoning on tool_use_plan
"USE_OLLAMA_DEEPSEEK": "", // "true" if you want to use deepseek with local ollama, default is false
"OLLAMA_URL": "" // default with http://localhost:11434
}
}
}
}
gemini
Gemini-powered search
fetch
Fetch tools
brave_search
Brave Search tools
google_maps
Google Maps tools
confluence
Confluence tools
youtube
YouTube tools
jira
Jira tools
gitlab
GitLab tools
script
Script tools
rag
RAG tools
deepseek
Deepseek AI tools, including reasoning and advanced search if 'USE_OLLAMA_DEEPSEEK' is set to true, default ollama endpoint is http://localhost:11434 with model deepseek-r1:8b
action
(String) (Required): Action to perform: list, enable, disable
tool_name
(String): Tool name to enable/disable
request
(String) (Required): Request to plan for
context
(String) (Required): Context related to the request
There is a hidden variable ENABLE_TOOLS in the environment variable. It is a comma separated list of tools group to enable. If not set, all tools will be enabled. Leave it empty to enable all tools.
Here is the list of tools group:
- gemini: Gemini-powered search
- fetch: Fetch tools
- brave_search: Brave Search tools
- google_maps: Google Maps tools
- confluence: Confluence tools
- youtube: YouTube tools
- jira: Jira tools
- gitlab: GitLab tools
- script: Script tools
- rag: RAG tools
- deepseek: Deepseek AI tools, including reasoning and advanced search if 'USE_OLLAMA_DEEPSEEK' is set to true, default ollama endpoint is http://localhost:11434 with model deepseek-r1:8b
Manage MCP tools - enable or disable tools
Arguments:
- action (String) (Required): Action to perform: list, enable, disable
- tool_name (String): Tool name to enable/disable
Create a plan using available tools to solve the request
Arguments:
- request (String) (Required): Request to plan for
- context (String) (Required): Context related to the request
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"aio-mcp server": {
"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": ""
}
}
}
}
}
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": ""
}
}
}
A powerful Model Context Protocol (MCP) server implementation with integrations for GitLab, Jira, Confluence, YouTube, and more. This server provides AI-powered search capabilities and various utility tools for development workflows.
Prerequisites
- Go 1.23.2 or higher
- Various API keys and tokens for the services you want to use
Installation
Installing via Smithery
To install AIO-MCP Server for Claude Desktop automatically via Smithery (will guide you through interactive CLI setup):
npx -y @smithery/cli install @athapong/aio-mcp --client claude
Note: Smithery will interactively prompt you for required configuration values and handle environment setup automatically
Installing via Go
To set the go install command to install into the Go bin path, you need to ensure your Go environment variables are correctly configured. Here's how to do it:
1. First, ensure you have a properly set GOPATH environment variable, which by default is $HOME/go on Unix-like systems or %USERPROFILE%\go on Windows.
2. The go install command places binaries in $GOPATH/bin by default. Make sure this directory is in your system's PATH environment variable.
Here's how to set this up on different operating systems:
Linux/macOS:
```bashSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



