mcpField
A
Agent.AI MCP Server

Agent.AI MCP Server

Local
github.com/dschwartzAIAI & Agents0Updated 73w ago

About Agent.AI MCP Server

An externally deployable version of the Agent.AI MCP Server, intended for hosting on Vercel and use by other applications. It requires an Agent.AI API token configured as an environment variable.

Key features

  1. 01Deploy on Vercel
  2. 02Run locally on port 3000 by default
  3. 03Configure environment variables in Vercel
  4. 04Authenticate with an Agent.AI API token

Use cases

  1. 01Host an Agent.AI MCP endpoint for other applications
  2. 02Run the server locally during development
  3. 03Configure the API token for a Vercel deployment

MCP support

Provides an MCP server endpoint that other applications can call after deployment. The README does not specify the MCP tools or resources it exposes.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Agent.AI MCP Server

This is an externally deployable version of the Agent.AI MCP Server, designed to be hosted on Vercel and called from other applications.

Deployment Instructions

Prerequisites
  • GitHub account
  • Vercel account (free tier works)
  • Git installed locally
Steps to Deploy
  1. Create a new GitHub repository

    git init
    git add .
    git commit -m "Initial commit: Agent.AI MCP Server"
    git branch -M main
    git remote add origin https://github.com/YOUR_USERNAME/agentai-mcp-server.git
    git push -u origin main
    
  2. Deploy to Vercel

    • Go to vercel.com
    • Click "New Project"
    • Import your GitHub repository
    • Vercel will automatically detect it as a Node.js project
    • Click "Deploy"
  3. Get your deployment URL

    • After deployment, Vercel will provide a URL like: https://your-project-name.vercel.app
    • This is your MCP server endpoint

Usage

Once deployed, you can call your MCP server from other applications using the Vercel URL.

Example Usage
// In your other app
const mcpServerUrl = 'https://your-project-name.vercel.app';

// Make requests to your MCP server
fetch(mcpServerUrl + '/your-endpoint')
  .then(response => response.json())
  .then(data => console.log(data));

Local Development

To run locally:

npm install
npm start

The server will start on http://localhost:3000

Configuration

  • Port: Automatically set by Vercel, or defaults to 3000 locally
  • Environment Variables: Can be set in Vercel dashboard under Project Settings > Environment Variables

Troubleshooting

  • Ensure your @agentai/mcp-server package is publicly available
  • Check Vercel deployment logs if issues occur
  • Verify your GitHub repository is public or Vercel has access

Important: Authentication Setup

1. Configure Agent.AI API Token

Your MCP server requires an Agent.AI API token to authenticate with Agent.AI services:

  1. Get your API token from Agent.AI
  2. Go to your Vercel project dashboard
  3. Click "Settings" → "Environment Variables"
  4. Add a new variable:
    • Name: API_TOKEN
    • Value: Your Agent.AI API token
  5. Redeploy the project
2. Disable Vercel Authentication

To allow external access to your MCP server, you MUST disable Vercel's built-in authentication:

  1. Go to your Vercel project dashboard
  2. Click "Settings" → "Security"
  3. Disable "Password Protection" and "Vercel Authentication"
  4. Save changes
3. Test Authentication

After setup, your endpoints will return:

  • ✅ "authentication": "configured" - Ready to use
  • ❌ "authentication": "missing" - API_TOKEN required

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.