AIPOLabs

v1.0.0APIsstable

A Model Context Protocol server that provides access to ACI.dev functions (tools) through either direct app-specific tools or a unified interface with dynamic tool discovery and execution based on user intent.

aipolabs-mcp-servermcpai-integration
Share:
250
Stars
0
Downloads
0
Weekly
0/5

What is AIPOLabs?

AIPOLabs is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol server that provides access to aci.dev functions (tools) through either direct app-specific tools or a unified interface with dynamic tool discovery and execution based on user ...

A Model Context Protocol server that provides access to ACI.dev functions (tools) through either direct app-specific tools or a unified interface with dynamic tool discovery and execution based on user intent.

This server falls under the APIs category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A Model Context Protocol server that provides access to ACI.

Use Cases

ACI.dev function integration
Dynamic tool discovery and execution
LicenseMIT License
Languagepython
Versionv1.0.0
UpdatedMay 15, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx aipolabs-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use AIPOLabs

The AIPOLabs MCP Server (aci-mcp) connects any MCP-compatible AI client to the ACI.dev platform, which provides a curated library of pre-built integrations with popular apps and services. It offers two operational modes: an Apps Server that exposes direct tool functions from specific named applications, and a Unified Server that provides two meta-functions — ACI_SEARCH_FUNCTIONS and ACI_EXECUTE_FUNCTION — enabling dynamic discovery and execution of any function across the entire ACI.dev catalog based on user intent. Developers use it to give their AI assistants access to hundreds of third-party services without individually implementing each API integration.

Prerequisites

  • Python 3 with uv package manager installed (curl -sSf https://install.pypa.io/get-pip.py | python3 - && pip install uv)
  • An ACI.dev account with a valid ACI_API_KEY
  • A LINKED_ACCOUNT_OWNER_ID from the ACI.dev dashboard for authentication
  • An MCP client such as Claude Desktop, Claude Code, or any MCP-compatible host
  • Optional: Docker for containerized deployment
1

Install uv and verify Python environment

ACI MCP uses uvx for direct execution without a global install. Install uv first if not already present.

curl -sSf https://install.pypa.io/get-pip.py | python3 -
pip install uv

# Verify
uvx aci-mcp --help
2

Obtain API credentials from ACI.dev

Sign up at ACI.dev and retrieve your ACI_API_KEY and LINKED_ACCOUNT_OWNER_ID from the dashboard. These are required for all server modes.

# Set as environment variables
export ACI_API_KEY=your_aci_api_key_here
export LINKED_ACCOUNT_OWNER_ID=your_linked_account_owner_id
3

Run the Unified Server

The Unified Server exposes ACI_SEARCH_FUNCTIONS and ACI_EXECUTE_FUNCTION tools, letting the AI dynamically discover and call any integration at runtime.

uvx aci-mcp unified-server \
  --linked-account-owner-id $LINKED_ACCOUNT_OWNER_ID
4

Run the Apps Server for specific integrations

The Apps Server pre-loads tools from specific named apps, providing direct function access without dynamic discovery overhead.

uvx aci-mcp apps-server \
  --apps "BRAVE_SEARCH,GMAIL" \
  --linked-account-owner-id $LINKED_ACCOUNT_OWNER_ID
5

Debug with MCP Inspector

Use the MCP Inspector to interactively test tools before connecting to a production client.

npx @modelcontextprotocol/inspector uvx aci-mcp unified-server \
  --linked-account-owner-id $LINKED_ACCOUNT_OWNER_ID
6

Deploy with Docker (optional)

For production deployments, build and run the Docker image with your API key injected as an environment variable.

docker build -t aci-mcp .
docker run --rm -i \
  -e ACI_API_KEY=$ACI_API_KEY \
  aci-mcp unified-server

AIPOLabs Examples

Client configuration

Claude Desktop configuration for the ACI MCP Unified Server using uvx

{
  "mcpServers": {
    "aci-unified": {
      "command": "uvx",
      "args": [
        "aci-mcp",
        "unified-server",
        "--linked-account-owner-id",
        "your_linked_account_owner_id"
      ],
      "env": {
        "ACI_API_KEY": "your_aci_api_key_here"
      }
    }
  }
}

Prompts to try

Example prompts for using ACI integrations through the MCP server

- "Search for the latest news about AI using Brave Search"
- "Find all available tools for Gmail integration"
- "Send an email to [email protected] with subject 'Weekly Update'"
- "What integrations are available for calendar and scheduling?"
- "Search ACI functions for Slack messaging capabilities"

Troubleshooting AIPOLabs

Authentication error: ACI_API_KEY invalid or missing

Confirm ACI_API_KEY is set correctly in your environment or in the MCP server env block. Retrieve a fresh key from the ACI.dev dashboard if the current one has expired or been revoked.

LINKED_ACCOUNT_OWNER_ID not found error

Log in to ACI.dev and navigate to your account settings to find the correct LINKED_ACCOUNT_OWNER_ID. This ID links the MCP session to your specific ACI.dev account and linked third-party app authorizations.

uvx command not found

Install uv with pip install uv or via the official uv installer at https://astral.sh/uv. After installation, ensure the uv binary directory is in your PATH by running which uvx.

Frequently Asked Questions about AIPOLabs

What is AIPOLabs?

AIPOLabs is a Model Context Protocol (MCP) server that model context protocol server that provides access to aci.dev functions (tools) through either direct app-specific tools or a unified interface with dynamic tool discovery and execution based on user intent. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install AIPOLabs?

Follow the installation instructions on the AIPOLabs GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with AIPOLabs?

AIPOLabs works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is AIPOLabs free to use?

Yes, AIPOLabs is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More APIs MCP Servers

Explore all apis servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "aipolabs-mcp-server": { "command": "npx", "args": ["-y", "aipolabs-mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use AIPOLabs?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides