Happy slice of mcp pizzaMCP.pizza

aci

MCP.Pizza Chef: aipotheosis-labs

ACI.dev is a powerful open-source infrastructure platform designed to unify MCP servers by connecting AI agents to over 600 tool integrations. It supports multi-tenant authentication and granular permission controls, enabling secure and scalable access management. ACI.dev facilitates direct function calling or interaction through a unified MCP server interface, making it ideal for developers building AI-enhanced workflows, agents, and copilots. With comprehensive documentation, active community support, and an Apache 2.0 license, ACI.dev streamlines the integration of diverse tools and APIs into AI environments, enhancing real-time context and interaction capabilities.

Use This MCP server To

Connect AI agents to diverse tool integrations securely Manage multi-tenant authentication for AI workflows Implement granular permission controls for tool access Enable direct function calling from AI models Unify multiple tool APIs under a single MCP server Build scalable AI-enhanced workflows and copilots Facilitate real-time context sharing across tools Integrate 600+ tools into AI agent environments

README

ACI.dev Logo

ACI: Open-Source Infra to Power Unified MCP Servers

aipotheosis-labs%2Faci | Trendshift

Documentation PyPI version License Discord Twitter Follow

Note

This repo is for the ACI.dev platform. If you're looking for the Unified MCP server built with ACI.dev, see aci-mcp.

ACI.dev is the open-source infrastructure layer for AI-agent tool-use. It gives your agents intent-aware access to 600+ tools with multi-tenant auth, granular permissions, and dynamic tool discovery—exposed as either direct function calls or through a Unified Model-Context-Protocol (MCP) server.

Example: Instead of writing separate OAuth flows and API clients for Google Calendar, Slack, and more, use ACI.dev to manage authentication and provide your AI agents with unified, secure function calls. Access these capabilities through our Unified MCP server or via our lightweight Python SDK, compatible with any LLM framework.

Build production-ready AI agents without the infrastructure headaches.

ACI.dev Architecture

Join us on Discord to help shape the future of Open Source AI Infrastructure.

🌟 Star ACI.dev to stay updated on new releases!

GitHub Stars

📺 Demo Video

ACI.dev Unified MCP Server Demo

ACI.dev Unified MCP Server Demo

✨ Key Features

  • 600+ Pre-built Integrations: Connect to popular services and apps in minutes.
  • Flexible Access Methods: Use our unified MCP server or our lightweight SDK for direct function calling.
  • Multi-tenant Authentication: Built-in OAuth flows and secrets management for both developers and end-users.
  • Enhanced Agent Reliability: Natural language permission boundaries and dynamic tool discovery.
  • Framework & Model Agnostic: Works with any LLM framework and agent architecture.
  • 100% Open Source: Everything released under Apache 2.0 (backend, dev portal, integrations).

💡 Why Use ACI.dev?

ACI.dev solves your critical infrastructure challenges for production-ready AI agents:

  • Authentication at Scale: Connect multiple users to multiple services securely.
  • Discovery Without Overload: Find and use the right tools without overwhelming LLM context windows.
  • Natural Language Permissions: Control agent capabilities with human-readable boundaries.
  • Build Once, Run Anywhere: No vendor lock-in with our open source, framework-agnostic approach.

🧰 Common Use Cases

  • Personal Assistant Chatbots: Build chatbots that can search the web, manage calendars, send emails, interact with SaaS tools, etc.
  • Research Agent: Conducts research on specific topics and syncs results to other apps (e.g., Notion, Google Sheets).
  • Outbound Sales Agent: Automates lead generation, email outreach, and CRM updates.
  • Customer Support Agent: Provides answers, manages tickets, and performs actions based on customer queries.

🔗 Quick Links

💻 Getting Started: Local Development

To run the full ACI.dev platform (backend server and frontend portal) locally, follow the individual README files for each component:

👋 Contributing

We welcome contributions! Please see our CONTRIBUTING.md for more information.

Integration Requests

Missing any integrations (apps or functions) you need? Please see our Integration Request Template and submit an integration request! Or, if you're feeling adventurous, you can submit a PR to add the integration yourself!

Star History

Star History Chart

aci FAQ

How does ACI.dev handle multi-tenant authentication?
ACI.dev provides built-in multi-tenant authentication mechanisms to securely manage access for multiple users or organizations within the same MCP server environment.
Can I control permissions for individual tool integrations?
Yes, ACI.dev supports granular permission settings, allowing fine-tuned access control for each tool integration per user or tenant.
How do AI agents interact with tools via ACI.dev?
AI agents can interact through direct function calls or via a unified MCP server interface that abstracts multiple tool APIs.
Is ACI.dev compatible with different LLM providers?
Yes, ACI.dev is provider-agnostic and works seamlessly with OpenAI, Anthropic Claude, and Google Gemini models.
What licensing governs ACI.dev?
ACI.dev is released under the Apache 2.0 open-source license, allowing flexible use and modification.
Where can I find documentation and community support?
Comprehensive documentation is available at aci.dev/docs, and community support is accessible via Discord and GitHub.
How scalable is ACI.dev for enterprise use?
Designed for scalability, ACI.dev supports multi-tenant environments and hundreds of tool integrations, suitable for enterprise-grade AI applications.
Does ACI.dev support real-time context updates?
Yes, it enables real-time context sharing and interaction across integrated tools to enhance AI agent capabilities.