Provides the foundation for the MCP Gateway, transforming FastAPI endpoints into MCP tools that allow LLMs to interact with corporate APIs in a controlled manner.
Supports project version control and distribution through Git repository cloning.
Hosts the FastAPI-MCP framework that this gateway is based on, allowing contribution and access to the core functionality.
Serves as the runtime environment for the MCP Gateway, with version 3.8+ required for operation.
MCP Gateway – API & Self-Service Portal
This repository contains the MCP Gateway, an enterprise solution to expose, manage and consume tools (internal APIs) in a secure, scalable and auditable way, with RBAC authentication and self-service portal.
Summary
Overview
The MCP Gateway consists of:
Backend: FastAPI + RBAC + JWT + JSON persistence (NoSQL ready)
Frontend: React (Vite) running integrated with the backend (build in
/frontend/dist
served as static)
Folder Structure
How to Spin (Development)
1. Backend (FastAPI)
2. Frontend (React)
Go to: http://localhost:5173 (dev) or http://localhost:8000 (prod)
3. Frontend Build for Production
The files will be generated in frontend/dist
. FastAPI can serve these files automatically.
Features
JWT Login (user, group admin, global admin)
Group, User, and Tool Management (CRUD)
Dynamic creation of tools by group admin
Safe consumption of tools via portal
Healthcheck, registration, automatic documentation (Swagger)
Ready for NoSQL database integration and SSO
RBAC Structure Example
See data/rbac.json
for example users, groups, and permissions.
Security
JWT, RBAC, share registry
Ready for CORS, HTTPS, rate limiting, etc.
API Documentation
Go to /docs
for Swagger or /redoc
for Redoc.
System Requirements
See the docs/REQUISITOS.md
file for detailed functional, non-functional, and business requirements.
Complete Documentation
Detailed project documentation is centralized in the docs/
folder:
docs/REQUISITOS.md
: System requirementsdocs/API.md
: Endpoints and API usage examplesdocs/ARQUITETURA.md
: Technical architecturedocs/SEGURANCA.md
: Security and best practicesdocs/GOVERNANCA.md
: Governance and rolesdocs/OPERACIONAL.md
: Operation, monitoring and troubleshootingdocs/CHANGELOG.md
: Version history
Good Practices and Observations
Keep dependencies up to date.
Use virtual environments for Python.
Always build the frontend before deploying to production.
See the documentation for the other modules in
docs/
.Tip: Use issues and pull requests to propose changes and maintain a history of decisions.
This document should be reviewed and updated periodically to reflect changes in the design.
This server cannot be installed
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
A secure bridge that enables Large Language Models (LLMs) to interact with enterprise APIs and services in a controlled, contextualized way.
Related MCP Servers
- -securityFlicense-qualityA TypeScript-based server that provides a memory system for Large Language Models (LLMs), allowing users to interact with multiple LLM providers while maintaining conversation history and offering tools for managing providers and model configurations.Last updated -27
- -securityFlicense-qualityFacilitates enhanced interaction with large language models (LLMs) by providing intelligent context management, tool integration, and multi-provider AI model coordination for efficient AI-driven workflows.Last updated -
- -securityAlicense-qualityBridges Large Language Models with Language Server Protocol interfaces, allowing LLMs to access LSP's hover information, completions, diagnostics, and code actions for improved code suggestions.Last updated -71MIT License
- -securityFlicense-qualityA unified Model Context Protocol Gateway that bridges LLM interfaces with various tools and services, providing OpenAI API compatibility and supporting both synchronous and asynchronous tool execution.Last updated -1