What are the prerequisites for running the server?
Python 3.8+ and access to running Tufin SecureTrack and SecureChange instances (v25.1 compatible). Docker is optional for containerized deployment.
@stonecircle82
Basic information
Bridge Tufin APIs to AI workflows: An open-source REST server with RBAC for SecureTrack and SecureChange integration.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"tufin-mcp": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
The Tufin MCP Server bridges Tufin's SecureTrack and SecureChange APIs with modern AI workflows. It provides a secure, standardized REST API with Role-Based Access Control (RBAC) for integrating Tufin data and actions into custom scripts, applications, and AI agents.
Clone the repository, create a Python virtual environment, install dependencies, configure environment variables (for Tufin connection and API keys), and run the server locally with Uvicorn or via Docker. Clients authenticate by passing an API key in the X-API-Key header.
Python 3.8+ and access to running Tufin SecureTrack and SecureChange instances (v25.1 compatible). Docker is optional for containerized deployment.
Clients provide an API key via the `X-API-Key` header. Keys are hashed with bcrypt and stored in an in‑memory store (for development) or a secure production store. Each key has a role that determines endpoint access via RBAC.
Modify the `ENDPOINT_PERMISSIONS` dictionary in `src/app/core/config.py` to assign roles (`admin`, `ticket_manager`, `user`) to each permission ID. Endpoints use `require_permission()` to enforce these permissions.
Yes, set `TUFIN_SSL_VERIFY` to `True` (default) to verify certificates. Disabling it (`False`) is insecure and only recommended for environments with self‑signed certificates.
Default rate limit: 60 requests per minute per IP address. Exceeding this returns HTTP 429. The limit is enforced through IP‑based rate limiting middleware.

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

Model Context Protocol Servers
Free moving quotes for AI agents from Next Generation Movers, a licensed interstate mover (USDOT 3764697). US long-distance nationwide and local DC/MD/VA. Indicative ballpark price and booking options; optional $0.01 x40
A search tool helps dev to solve the naming things problem.
🚀 The fast, Pythonic way to build MCP servers and clients.
Comments