Cursor Setup

Connect Cursor to Agiflow using the our Http MCP for seamless project management and code generation.

Prerequisites

Cursor installed

Download from cursor.com

Agiflow account and project

Create a free account at agiflow.io

Setup via Http MCP

Get Your Configuration

From your Agiflow dashboard, navigate to your project and click the Actions menu, then select Project MCP.

In the MCP setup dialog, select Http MCP as the setup method. You can use either Oauth2 or API key for MCP authorization.

You'll see two sections: environment variables and MCP configuration JSON.

Set Environment Variables (API key only)

Copy the export commands from the setup dialog and add them to your shell profile:

# Add to ~/.bashrc, ~/.zshrc, or ~/.profile
export AGIFLOW_MCP_API_KEY="your-generated-api-key"

💡 Tip: After adding these lines, run source ~/.zshrc (or your shell config file) to load the variables, or restart your terminal.

Configure Cursor MCP Settings

Open Cursor's MCP configuration file. In Cursor, go to Settings → MCP or directly edit:

# macOS/Linux
~/.cursor/mcp_settings.json

# Windows
%APPDATA%\Cursor\mcp_settings.json

Add MCP Server Configuration

Copy the JSON configuration from the Agiflow setup dialog and paste it into the mcpServers object:

Example configuration

{
  "mcpServers": {
    "agiflow-project-mcp": {
      "command": "http",
      "url": "https://agiflow.io/api/v1/projects/your-project-id/mcp",
      "env": {
        "AGIFLOW_MCP_API_KEY": "${AGIFLOW_MCP_API_KEY}"
      }
    }
  }
}

⚠️ Important: The configuration uses environment variable placeholders ($${VARIABLE}). Cursor will replace these with the actual values from your shell environment.

Restart Cursor

Completely restart Cursor (quit and reopen) to load the new MCP server configuration and environment variables.

Verify Connection

After setup, verify the connection by checking available MCP tools:

Open Cursor's command palette (Cmd/Ctrl + Shift + P)
Type "MCP" to see available MCP commands
Look for "agiflo" in the MCP servers list
Verify available tools include: describe-capabilities, use-capability, etc.

✅ Success!: Your Cursor is now connected to Agiflow. You can create tasks, manage work units, and use scaffolding templates directly from Cursor.

Troubleshooting

MCP server not appearing in Cursor

Verify the http endpoint is correct. We provided scoped MCP servers which have different endpoints. For Http MCP server, it should be ended with `/mcp`.

Getting connection errors

If you use Oauth, please try disconnect and reauthenticate the MCP server.
For API key, you can try generate another API key and replace to see if that works.
Check the proxy endpoint URL matches your organization and project IDs
Ensure the endpoint URL ends with /mcp-configs
Verify you have an active internet connection

Environment variables not loading

Make sure you added the export commands to the correct shell config file
Run source ~/.zshrc (or your shell config) to reload
For Cursor to pick up env vars, you may need to launch it from a terminal: cursor .
On macOS, try adding the variables to ~/.zprofile instead

Next Steps

@agiflowai/agent-cli

CLI tool for agent connections, session tracking, and model routing.

View Documentation

Project MCP

Explore all available project management tools and how to use them.