For the complete documentation index, see llms.txt. This page is also available as Markdown.

MCP Connection (Lovable)

What can you do with MCP?

When you enable the MCP server, external AI services can directly access your Manyfast planning files to learn from their contents, build on the planned structure, or carry out tasks based on it. This lets you extend your planning or move from planning to development quickly and consistently.

1. Auto-generate code from planning documents

  • Pass the Specifications defined in Manyfast through MCP to code Agents like Cursor or Claude Code to generate code that follows your plan and drive development forward.

2. Provide learning context to Agents

  • Provide consistent context to AI development Agents through Manyfast's planning structure and naming conventions.

3. Real-time sync between planning and development

  • The MCP server updates changes from Manyfast in real time, keeping the connected planning information up to date.

Manyfast MCP supports integration with the following services.

  • Cursor / Claude Code / ChatGPT / Lovable

How to Connect

Manyfast MCP can be used in Cursor, Claude Code, ChatGPT, and Lovable. Refer to the setup instructions for each environment below.

Adding the MCP Server

Cursor Setup

Cursor MCP Official Documentation

  • Go to Cursor's Settings > Integrations > "Custom MCP Server" and enter the following information.

{
  "mcpServers": {
    "manyfast": {
      "url": "https://api.manyfast.io/mcp"
    }
  }
}
  • From the list of installed MCP servers, proceed to connect to manyfast.

Once setup is complete, you'll be redirected to the login page to connect to the MCP server.

Logging In to the MCP Server

  • When you enable the MCP server, you'll be prompted to log in to complete the connection.

  • Once you've logged in with your Manyfast account, you can select the group to connect to the MCP server.

Last updated