AuraMCP - Universal MCP Server Generator
Generate MCP (Model Context Protocol) servers from any OpenAPI specification. Connect LLM agents to Slack, GitHub, Notion, Stripe, and 100+ other APIs instantly.
How It Works
AuraMCP is a generator tool that creates standalone MCP server packages:
- Install AuraMCP → The generator CLI
- Run
auramcp generate <provider>→ Creates a new Python package (e.g.,auramcp_slack) - Install the generated package →
pip install -e .in the output folder - Run the MCP server →
python -m auramcp_slack
Each generated server is independent and can be distributed separately.
Features
- Parse OpenAPI 2.0 & 3.x - Automatically handles both Swagger and OpenAPI specs
- Generate MCP Servers - Creates complete, runnable Python packages with FastMCP
- Auth Ready - Pre-configured authentication for popular APIs (OAuth2, API Key, Bearer)
- CLI & Programmatic - Use from command line or import as a library
- LLM Enhancement - Optional Claude-powered review and description enhancement
Installation
pip install auramcp
For LLM review features:
pip install auramcp[llm]
Quick Start
1. Generate a Server
# Generate MCP server for Slack
auramcp generate slack --output ./servers
# Generate with LLM review (optional)
auramcp generate notion --review --output ./servers
# List available providers
auramcp list
# Search for APIs
auramcp list --search "email"
# Get provider info
auramcp info github
2. Install and Run the Generated Server
Each generated server is a standalone pip package. After generation:
# Navigate to the generated server
cd servers/slack
# Install the generated package
pip install -e .
# Set the required environment variable (shown after generation)
export SLACK_BOT_TOKEN=xoxb-your-token
# Run the MCP server
python -m auramcp_slack
3. Connect to Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"slack": {
"command": "python",
"args": ["-m", "auramcp_slack"],
"env": {
"SLACK_BOT_TOKEN": "xoxb-your-token"
}
}
}
}
Note: The environment variable name depends on the provider and auth type. The CLI will show you the exact variable name after generation.
Programmatic Usage
from auramcp.generator import OpenAPIParser, MCPConverter, MCPCodeGenerator
# Parse an OpenAPI spec
parser = OpenAPIParser()
parsed = parser.parse("https://api.example.com/openapi.json")
# Convert to MCP tools
converter = MCPConverter()
tools = converter.convert(parsed)
# Generate server code
generator = MCPCodeGenerator()
server = generator.generate(
tools=tools,
server_name="myapi",
base_url=parsed.base_url,
auth_type="bearer",
)
# Write to disk
server.write("./output/myapi")
Supported Providers
Tier 1 (Production Ready)
- Slack
- GitHub
- Notion
- Stripe
- Airtable
- HubSpot
- Trello
- Discord
Tier 2 (Auto-generated + Reviewed)
- Asana, Linear, Jira
- Zendesk, Intercom
- Mailchimp, SendGrid, Twilio
- Shopify, Zoom, Calendly
- And 30+ more...
Tier 3 (Fully Automated)
- All 2000+ APIs from APIs.guru
Development
# Clone and install
git clone https://github.com/auramcp/auramcp.git
cd auramcp
pip install -e ".[dev]"
# Run tests
pytest
# Run example
python scripts/generate_example.py
Environment Variables
# For LLM review (optional)
ANTHROPIC_API_KEY=sk-ant-...
# Per-provider credentials (names shown after generation)
SLACK_BOT_TOKEN=xoxb-... # Slack (OAuth2/Bot token)
GITHUB_TOKEN=ghp_... # GitHub (Bearer token)
NOTION_TOKEN=secret_... # Notion (Bearer token)
STRIPE_API_KEY=sk_test_... # Stripe (API Key)
AIRTABLE_TOKEN=pat... # Airtable (Bearer token)
Tip: Run
auramcp info <provider>to see the required environment variable.
Architecture
auramcp/
├── generator/ # Core generator engine
│ ├── parser.py # OpenAPI 2.0/3.x parsing
│ ├── converter.py # OpenAPI → MCP tools
│ ├── codegen.py # Python code generation
│ └── reviewer.py # LLM enhancement
├── auth/ # Authentication layer
│ ├── registry.py # Auth config management
│ ├── handlers.py # OAuth2, API Key, Bearer
│ └── configs/ # Per-provider YAML configs
├── specs/ # Spec management
│ ├── fetcher.py # APIs.guru + first-party
│ └── registry.py # Provider index
└── cli.py # Command-line interface
License
MIT
Metadata
Release files for auramcp 0.1.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| auramcp-0.1.3.tar.gz | 31.5 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| auramcp-0.1.3-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 71.5 kB
Release files / auramcp-0.1.3.tar.gz
| Download URL | auramcp-0.1.3.tar.gz |
|---|---|
| Size | 31.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c81bce2574d25aeef7185d6ec3e38096bea1c5176f1f40d3909c1923d0c0128d
|
|
BLAKE2b-256 checksum How to use checksums |
97e7cde6a0dea576b415b1f7120fdb77490da2cd4383e519735f0ca61b70725b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.0
|
Release files / auramcp-0.1.3-py3-none-any.whl
| Download URL | auramcp-0.1.3-py3-none-any.whl |
|---|---|
| Size | 40.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a5a64b33fe9d036b89bc56cfc723e41c6a56242303e1f3b18d9a6ef31bbe1bd5
|
|
BLAKE2b-256 checksum How to use checksums |
143658a31c886503fd830abc61458d0a17963c05259a4e103f721b80261a22c2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.0
|
Security for auramcp 0.1.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.