Aipotheosis Labs' aci-mcp provides Model Context Protocol (MCP) servers designed to facilitate access to ACI.dev managed functions (tools). It targets developers and researchers integrating AI functions into applications, offering two distinct server implementations: one for specific application tools and another for unified discovery and execution of all available ACI.dev functions. This allows for flexible and controlled access to a broad range of AI capabilities.

How It Works

The package offers two MCP server types: aci-mcp-apps and aci-mcp-unified. The apps-server provides direct access to functions from pre-specified applications, enabling granular control. In contrast, the unified-server exposes meta-functions (ACI_SEARCH_FUNCTIONS, ACI_EXECUTE_FUNCTION) that allow clients to discover and execute any function available on the ACI.dev platform. This architecture simplifies tool integration by abstracting the underlying function management.

Quick Start & Requirements

Installation is straightforward via PyPI using uv:

pip install uv
uvx aci-mcp

To run servers:

uvx aci-mcp apps-server --apps <APP_NAME> --linked-account-owner-id
uvx aci-mcp unified-server --linked-account-owner-id

A valid ACI_API_KEY environment variable is required. Docker images are available for deployment. Debugging can be performed using npx @modelcontextprotocol/inspector or by tailing log files (~/Library/Logs/Claude/mcp*.log). Full documentation and tutorials are available at aci.dev docs.

Highlighted Details

• Provides two distinct MCP server implementations: apps-server for targeted function access and unified-server for comprehensive discovery and execution.
• The unified-server utilizes meta-functions (ACI_SEARCH_FUNCTIONS, ACI_EXECUTE_FUNCTION) for dynamic tool interaction.
• Includes Dockerfiles for containerized deployment and integration.
• Offers debugging utilities, including an MCP inspector and server log monitoring.

Maintenance & Community

No specific information regarding maintainers, community channels (e.g., Discord, Slack), sponsorships, or roadmap is present in the provided README.

Licensing & Compatibility

The README does not specify a software license. Consequently, compatibility for commercial use or linking with closed-source projects cannot be determined without further information.

Limitations & Caveats

The provided README focuses solely on basic development guidance, explicitly directing users to external documentation (aci.dev docs) for comprehensive details and tutorials. The absence of a stated license poses a significant adoption blocker, preventing clear understanding of usage rights and restrictions.