MCP server
by saharmor
Run Augment Code with Auggie CLI—your AI powered coding assistant and AI code helper for smarter, faster coding.
Integrates Augment Code's Auggie CLI to answer questions about your codebase and implement code changes through an MCP interface.
Auggie (Augment Code) is a community-built MCP server published by saharmor that provides AI assistants with tools and capabilities via the Model Context Protocol. Run Augment Code with Auggie CLI—your AI powered coding assistant and AI code helper for smarter, faster coding. It is categorized under developer tools.
You can install Auggie (Augment Code) in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
Auggie (Augment Code) is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
We wired Auggie (Augment Code) into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
Auggie (Augment Code) has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
Auggie (Augment Code) is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
According to our notes, Auggie (Augment Code) benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
We wired Auggie (Augment Code) into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
According to our notes, Auggie (Augment Code) benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Useful MCP listing: Auggie (Augment Code) is the kind of server we cite when onboarding engineers to host + tool permissions.
Auggie (Augment Code) is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
We wired Auggie (Augment Code) into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
Auggie (Augment Code) is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
showing 1-10 of 42
Minimal MCP server exposing Auggie CLI as tools for Q&A and code implementation.
auggie --version) - see installation guideRetrieve your token via the Auggie CLI:
# Ensure Auggie CLI is installed and on PATH
auggie --version
# Sign in (opens browser flow)
auggie login
# Print your token
auggie --print-augment-token
Provide the token in either of these ways:
env for the server{
"mcpServers": {
"auggie-mcp": {
"command": "npx",
"args": ["-y", "auggie-mcp@latest"],
"env": { "AUGMENT_API_TOKEN": "YOUR_TOKEN" }
}
}
}
One-off for a single command:
AUGMENT_API_TOKEN=YOUR_TOKEN npx -y auggie-mcp --setup-only
Persist for future shells (zsh):
echo 'export AUGMENT_API_TOKEN=YOUR_TOKEN' >> ~/.zshrc
source ~/.zshrc
Security tip: never commit tokens to source control. Prefer per-machine environment variables or your client's secure config store.
Use this MCP config in Cursor (global or per-project):
{
"mcpServers": {
"auggie-mcp": {
"command": "npx",
"args": ["-y", "auggie-mcp@latest"],
"env": { "AUGMENT_API_TOKEN": "YOUR_TOKEN" }
}
}
}
This will:
requirements.txt, andstdio mode.# Install deps into the package's local venv (no global installs)
npx -y auggie-mcp --setup-only
# Run the server (stdio). Useful for quick smoke-tests.
npx -y auggie-mcp
# Optional: start HTTP mode for manual debugging
npx -y auggie-mcp -- --http
Edit ~/Library/Application Support/Claude/claude_desktop_config.json and add:
{
"mcpServers": {
"auggie-mcp": {
"command": "npx",
"args": ["-y", "auggie-mcp@latest"],
"env": { "AUGMENT_API_TOKEN": "YOUR_TOKEN" }
}
}
}
implement runs in dry‑run mode. No files are written, no shell runs; you get a proposed diff.dry_run: false.Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.