MCP Gateway
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.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Gatewayrequest access to the sales dashboard API"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
Related MCP server: Model Context Provider (MCP) Server
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/distserved as static)
Folder Structure
mcp-server/
├── app/ # Backend FastAPI
│ ├── main.py # Entrypoint
│ ├── config.py # Configurações
│ ├── auth.py # Autenticação/JWT
│ ├── utils/ # Utilitários (RBAC, dependências)
│ └── groups/
│ ├── routes.py # Rotas (APIs)
│ └── tools.py # Utilitários de permissão
├── data/ # Dados persistentes
│ └── rbac.json # Usuários, grupos, permissões
├── frontend/ # Portal React (Vite)
│ ├── src/ # Código-fonte React
│ └── dist/ # Build de produção (servido pelo FastAPI)
├── requirements.txt # Dependências Python
├── README.md # Este documento
└── ...How to Spin (Development)
1. Backend (FastAPI)
python -m venv venv
.\venv\Scripts\activate
pip install -r requirements.txt
uvicorn app.main:app --reload2. Frontend (React)
cd frontend
npm install
npm run devGo to: http://localhost:5173 (dev) or http://localhost:8000 (prod)
3. Frontend Build for Production
cd frontend
npm run buildThe 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
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA 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.27
- AlicenseNot gradedqualityDmaintenanceFacilitates 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.MIT
- AlicenseNot gradedqualityFmaintenanceBridges 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.3,520123MIT
- FlicenseNot gradedqualityFmaintenanceA 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.1
Related MCP Connectors
Shared, permission-aware company context for AI agents, with provenance, approvals and audit.
Enterprise AI Control Plane: governance, guardrails, spend tracking, compliance & smart routing.
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jowpereira/mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server