all-in-one-model-context-protocol
π All-in-one MCP server with AI search, RAG, and multi-service integrations (GitLab/Jira/Confluence/YouTube) for AI-enhanced development workflows
claude mcp add --transport stdio nguyenvanduocit-all-in-one-model-context-protocol all-in-one-model-context-protocol -env /path/to/.env \ --env KEY_PATH="Path to TLS key (if needed)" \ --env CERT_PATH="Path to TLS certificate (if needed)" \ --env PROXY_URL="Proxy URL if you route traffic through a proxy" \ --env GITLAB_HOST="Base URL for GitLab instance" \ --env QDRANT_HOST="Vector store host for Qdrant" \ --env QDRANT_PORT="Vector store port for Qdrant" \ --env ENABLE_TOOLS="Comma-separated tool groups to enable (e.g., gemini, fetch, confluence, youtube, jira, gitlab, script, rag, deepseek). Leave empty to enable all tools." \ --env GITHUB_TOKEN="GitHub token (if using GitHub integrations)" \ --env GITLAB_TOKEN="Access token for GitLab API" \ --env BRAVE_API_KEY="API key for Brave-related features (if applicable)" \ --env OPENAI_ORG_ID="OpenAI Organization ID (optional)" \ --env ATLASSIAN_HOST="Base URL for Atlassian (Confluence/Jira) APIs" \ --env BRAVE_API_HOST="Host for Brave-related services (if applicable)" \ --env BRAVE_API_PORT="Port for Brave API (if applicable)" \ --env OPENAI_API_KEY="OpenAI API key" \ --env QDRANT_API_KEY="API key for Qdrant (if required)" \ --env ATLASSIAN_EMAIL="Email for Atlassian account" \ --env ATLASSIAN_TOKEN="API token for Atlassian" \ --env YOUTUBE_API_KEY="YouTube API key (if using YouTube tools)" \ --env DEEPSEEK_API_KEY="Deepseek API key" \ --env GOOGLE_AI_API_KEY="Google AI API key (for Gemini/Google integrations)" \ --env GOOGLE_TOKEN_FILE="Path to Google token file (for Google services)" \ --env GOOGLE_CREDENTIALS_FILE="Path to Google service account credentials file"
How to use
MyMCP Server (MyMCP) is designed to provide a centralized Model Context Protocol (MCP) server with integration points to a range of tools and services such as Atlassian products, Google services, GitLab, YouTube, Confluence, Jira, and more. It exposes capabilities for knowledge retrieval, automation, and tooling within AI workflows. With the available tools, you can perform calendar operations, fetch web content, search knowledge bases, interact with project management and collaboration suites, and run script-based utilities. To run the server, configure your environment via a .env file and start the MCP server process; the server will load your tool integrations and expose the MCP endpoints for your AI agent or client to query. This setup enables seamless, context-rich queries to access calendars, Confluence pages, Jira issues, GitLab projects, and other connected services from within prompts and workflows.
How to install
Prerequisites:
- Go 1.23.2 or higher installed on your system
- Access to the internet to install modules and dependencies
Installation steps:
- Install the server via Go:
go install github.com/nguyenvanduocit/all-in-one-model-context-protocol@latest
- Create a .env file with your configuration (example placeholders shown):
ENABLE_TOOLS=
QDRANT_HOST=
ATLASSIAN_HOST=
ATLASSIAN_EMAIL=
GITLAB_HOST=
GITLAB_TOKEN=
BRAVE_API_KEY=
ATLASSIAN_TOKEN=
GOOGLE_AI_API_KEY=
PROXY_URL=
OPENAI_API_KEY=
DEEPSEEK_API_KEY=
QDRANT_PORT=
GOOGLE_TOKEN_FILE=
GOOGLE_CREDENTIALS_FILE=
QDRANT_API_KEY=
- Run or configure the MCP server in your client config (see below for example):
{
"mcpServers": {
"my_mcp_server": {
"command": "all-in-one-model-context-protocol",
"args": ["-env", "/path/to/.env"]
}
}
}
Optional: If you prefer, you can also install via Smithery (interactive CLI) as shown in the project notes, but the official Go route is provided above.
Additional notes
Tips:
- The ENABLE_TOOLS environment variable controls which tool groups are active. If left empty, all tools enabled by default.
- Ensure your .env file paths are correct and accessible by the MCP process.
- Some integrations (e.g., Google or Atlassian) require API keys or service account credentials; ensure these are generated in the respective console and pointed to by GOOGLE_TOKEN_FILE, GOOGLE_CREDENTIALS_FILE, and ATLASSIAN_TOKEN.
- For Google-related features, Google Credentials and Tokens may be sensitive; restrict file access and rotate keys periodically.
- If you encounter connectivity issues to external services, verify PROXY_URL settings and network egress permissions.
- When updating dependencies, re-check that your environment variable names match the updated tool integrations.
Related MCP Servers
mcp-language
mcp-language-server gives MCP enabled clients access semantic tools like get definition, references, rename, and diagnostics.
obsidian -tools
Add Obsidian integrations like semantic search and custom Templater prompts to Claude or any MCP client.
openapi
OpenAPI definitions, converters and LLM function calling schema composer.
neurolink
Universal AI Development Platform with MCP server integration, multi-provider support, and professional CLI. Build, test, and deploy AI applications with multiple ai providers.
Pare
Dev tools, optimized for agents. Structured, token-efficient MCP servers for git, test runners, npm, Docker, and more.
brainstorm
MCP server for multi-round AI brainstorming debates between multiple models (GPT, DeepSeek, Groq, Ollama, etc.)