Navigation
MCP Servers Powered by: Enterprise AI Compute & Scalability - MCP Implementation

MCP Servers Powered by: Enterprise AI Compute & Scalability

Deliver mission-critical scale with MCP servers powered by Aipolabs ACI.dev - enterprise-grade compute optimized for AI workloads and seamless scalability.

Developer Tools
4.1(103 reviews)
154 saves
72 comments

Users create an average of 44 projects per month with this tool

About MCP Servers Powered by

What is MCP Servers Powered by: Enterprise AI Compute & Scalability?

MCP servers, driven by enterprise-grade AI compute and scalability, act as intermediaries between your applications and the expansive tool ecosystem of ACI.dev. These servers come in two flavors: the Apps Server, which grants direct access to predefined application tools, and the Unified Server, offering dynamic search and execution capabilities for any available tool on ACI.dev. Think of them as your AI-powered control centers for automating workflows and integrating diverse tools without manual configuration overhead.

How to Use MCP Servers Powered by: Enterprise AI Compute & Scalability?

Getting started involves three key steps:

  1. Set up authentication: Configure your ACI.dev API key via the AIPOLABS_ACI_API_KEY environment variable.
  2. Select your server type:
    • For targeted access: Use aipolabs-mcp-apps with specific apps like BRAVE_SEARCH or GMAIL.
    • For universal access: Deploy aipolabs-mcp-unified to dynamically search and execute any tool.
  3. Integrate with tools: Configure servers in platforms like Claude Desktop or Cursor via JSON configurations for seamless workflow automation.

MCP Servers Powered by Features

Key Features of MCP Servers Powered by: Enterprise AI Compute & Scalability?

These servers shine with their:

  • Dynamic Discovery: The Unified Server’s AI-driven search (ACI_SEARCH_FUNCTIONS_WITH_INTENT) intelligently finds tools matching your intent, bypassing the need to pre-configure thousands of options.
  • Seamless Scalability: Handle fluctuating workloads effortlessly—ideal for projects requiring sudden bursts of tool executions without performance bottlenecks.
  • Fine-Grained Control: Restrict access to specific apps or allow full platform access via flags like --allowed-apps-only.
  • Context Window Optimization: Avoid bloating your LLM’s context by deferring tool discovery until execution time.

Use Cases of MCP Servers Powered by: Enterprise AI Compute & Scalability?

Perfect for scenarios like:

  • Marketing Automation: Dynamically search ACI.dev for tools like email marketing platforms or analytics integrations without predefined setup.
  • Cross-Platform Workflows: Tie together tools from multiple apps (e.g., Gmail for notifications + Google Sheets for data logging) in a single workflow.
  • Enterprise Resource Management: Scale function executions during peak demand periods without manual server adjustments.
  • On-Demand Tool Access: Let your LLM "discover as it goes" for use cases where requirements evolve unpredictably.

MCP Servers Powered by FAQ

FAQ from MCP Servers Powered by: Enterprise AI Compute & Scalability?

How do I choose between Apps and Unified Servers?

Opt for the Apps Server when you need direct access to specific tools (e.g., a dedicated Gmail integration). Use the Unified Server when you want flexibility to leverage any ACI.dev tool dynamically, perfect for evolving workflows.

What happens if I forget my LINKED_ACCOUNT_OWNER_ID?

This critical identifier is tied to your ACI.dev account’s linked resources. Retrieve it through the project settings dashboard—it’s like the master key for connecting your tools to the server.

Can I combine both server types?

Absolutely! Deploy the Apps Server for core tools and the Unified Server for on-demand access. Just ensure each server’s environment variables are properly isolated to avoid conflicts.

Content

MCP servers powered by ACI.dev

Table of Contents

  • Overview
  • Prerequisites
  • Installation
  • Usage
    • Apps Server
    • Unified Server
  • Understanding the Two Server Types
    • Apps Server
    • Unified Server
  • Configuration
    • Usage with Claude Desktop
    • Usage with Cursor
  • FAQ
  • Debugging

Overview

This package provides two Model Context Protocol (MCP) servers for accessing ACI.dev managed functions (tools):

  • aipolabs-mcp-apps: An MCP server that provides direct access to functions (tools) from specified apps
  • aipolabs-mcp-unified: An MCP server that provides two meta functions (tools) (ACI_SEARCH_FUNCTIONS_WITH_INTENT and ACI_EXECUTE_FUNCTION) to discover and execute ALL functions (tools) available on ACI.dev

Prerequisites

Before using this package, you need to (for more information please see tutorial):

  1. Set the AIPOLABS_ACI_API_KEY environment variable with your ACI.dev API key
  2. Configure apps and set them in allowed_apps for your agent on platform.aci.dev.
  3. Link your app specific accounts under the same --linked-account-owner-id you'll later provide to start the MCP servers

Installation

The package is published to PyPI, so you can run it directly using uvx:

# Install uv if you don't have it already
curl -sSf https://install.pypa.io/get-pip.py | python3 -
pip install uv

Usage

Apps Server

The apps server provides direct access to functions (tools) under specific apps. You can specify one or more apps to use with the --apps parameter. (For a list of available apps, please visit ACI.dev)

# Using stdio transport (default)
uvx aipolabs-mcp apps-server --apps "BRAVE_SEARCH,GMAIL" --linked-account-owner-id <LINKED_ACCOUNT_OWNER_ID>

# Using SSE transport with custom port
uvx aipolabs-mcp apps-server --apps "BRAVE_SEARCH,GMAIL" --linked-account-owner-id <LINKED_ACCOUNT_OWNER_ID> --transport sse --port 8000

Unified Server

The unified server provides two meta functions (tools) to discover and execute ANY functions (tools) available on ACI.dev, even if they aren't directly listed in the server.

The functions (tools) are dynamically searched and executed based on your intent/needs. You don't need to worry about having thousands of tools taking up your LLM's context window or having to integrate multiple MCP servers.

# During functions (tools) search/discovery, allow discoverability of all functions (tools) available on ACI.dev
uvx aipolabs-mcp unified-server --linked-account-owner-id <LINKED_ACCOUNT_OWNER_ID>

# During functions (tools) search/discovery, limit to only functions (tools) accessible by the requesting agent (identified by AIPOLABS_ACI_API_KEY)
uvx aipolabs-mcp unified-server --linked-account-owner-id <LINKED_ACCOUNT_OWNER_ID> --allowed-apps-only

Understanding the Two Server Types

Apps Server

The apps server provides direct access to specific app functions/tools you specify with the --apps parameter. These tools will appear directly in the tool list when MCP clients (e.g. Claude Desktop, Cursor, etc.) interact with this server.

Unified Server

The unified server doesn't directly expose app-specific tools. Instead, it provides two meta functions (tools):

  1. ACI_SEARCH_FUNCTIONS_WITH_INTENT: Discovers functions (tools) based on your intent/needs
  2. ACI_EXECUTE_FUNCTION: Executes ANY function (tool) discovered by the search

This approach allows MCP clients to dynamically discover and use ANY function available on ACI.dev platform without needing to list them all upfront. It can search for the right tool based on your needs and then execute it.

Configuration

Usage with Claude Desktop

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "aipolabs-mcp-unified": {
      "command": "uvx",
      "args": ["aipolabs-mcp", "unified-server", "--linked-account-owner-id", "<LINKED_ACCOUNT_OWNER_ID>"]
    }
  }
}

For apps-specific access:

{
  "mcpServers": {
    "aipolabs-mcp-apps": {
      "command": "uvx",
      "args": ["aipolabs-mcp", "apps-server", "--apps", "BRAVE_SEARCH,GMAIL", "--linked-account-owner-id", "<LINKED_ACCOUNT_OWNER_ID>"]
    }
  }
}

Usage with Cursor

Add to your Cursor mcp.json:

{
    "mcpServers": {
      "aipolabs-mcp-unified": {
        "command": "uvx",
        "args": ["aipolabs-mcp", "unified-server", "--linked-account-owner-id", "<LINKED_ACCOUNT_OWNER_ID>"],
        "env": {
            "AIPOLABS_ACI_API_KEY": "<AIPOLABS_ACI_API_KEY>"
        }
      }
    }
  }

For apps-specific access:

{
  "mcpServers": {
    "aipolabs-mcp-apps": {
        "command": "uvx",
        "args": ["aipolabs-mcp", "apps-server", "--apps", "BRAVE_SEARCH,GMAIL", "--linked-account-owner-id", "<LINKED_ACCOUNT_OWNER_ID>"],
        "env": {
            "AIPOLABS_ACI_API_KEY": "<AIPOLABS_ACI_API_KEY>"
        }
    }
  }
}

FAQ

  • How do I get theAIPOLABS_ACI_API_KEY?

The AIPOLABS_ACI_API_KEY is the API key for your ACI.dev project. You can find it in the ACI.dev project settings.

  • How to configure Apps and allow access to them?

You can configure apps and allow access to them in the ACI.dev project settings.

  • How do I get theLINKED_ACCOUNT_OWNER_ID?

The LINKED_ACCOUNT_OWNER_ID is the ID of the account that you want to use to access the functions. You can find it in the ACI.dev project settings.

  • What is the benefit of using the unified server over the apps server?

Most of the current MCP servers are limited to a specific set of functions (tools), usually from a single app. If you need to use functions from multiple apps, you'll need to integrate multiple MCP servers. But even if you are ok with the managing overhead of integrating multiple MCP servers, your LLM tool calling performance might suffer because all the tools are loaded into the LLM's context window at once.

The unified server, however, allows you to discover and execute ANY function available on ACI.dev dynamically without worrying about having thousands of tools taking up your LLM's context window or having to integrate multiple MCP servers.

  • How to specify a list of apps to use with the apps server?

You can specify a comma-separated list of apps to use with the apps server using the --apps parameter. Try NOT to have spaces between the app names.

  • Can I just use functions (tools) from one app?

Yes, you can just use functions (tools) from one app by specifying the (one) app name with the --apps parameter.

Debugging

You can use the MCP inspector to debug the server:

# For unified server
npx @modelcontextprotocol/inspector uvx aipolabs-mcp unified-server --linked-account-owner-id <LINKED_ACCOUNT_OWNER_ID>

# For apps server
npx @modelcontextprotocol/inspector uvx aipolabs-mcp apps-server --apps "BRAVE_SEARCH,GMAIL" --linked-account-owner-id <LINKED_ACCOUNT_OWNER_ID>

Running tail -n 20 -f ~/Library/Logs/Claude/mcp*.log will show the logs from the server and may help you debug any issues.

Related MCP Servers & Clients