DreamFactory

Provides access to DreamFactory data sources and actions through Claude via MCP for secure, governed API access.
  • javascript

4

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "dreamfactorysoftware-df-mcp": {
      "command": "node",
      "args": [
        "/Users/dreamfactory/Documents/df-mcp/build/index.js"
      ],
      "env": {
        "DREAMFACTORY_URL": "https://example.dreamfactory.com/api/v2/<service-name>"
      }
    }
  }
}

DreamFactory MCP Server lets Claude Desktop talk to DreamFactory data sources and actions. It exposes a lightweight local server that you run alongside Claude Desktop, enabling seamless data access and operation through your Claude workflow.

How to use

Configure Claude Desktop to load the DreamFactory MCP server as a local process, then start Claude Desktop and enable the server in its Extensions/Developer settings. Once enabled, you can issue commands to DreamFactory via Claude’s interface, allowing you to query data sources, execute actions, and orchestrate DreamFactory operations directly from Claude.

Two practical usage patterns you can adopt are:

How to install

Prerequisites you need before installing: Node.js version 22.10.0 or newer. If you are using Node Version Manager (NVM) or other developer tools that alter Node paths, you may need to adjust your setup to ensure Claude Desktop uses the correct Node binary.

Manual installation steps:

#!/bin/bash
# Prerequisite: ensure Node is installed (node -v should be 22.10.0+)

# 1) Install dependencies for the MCP server
cd df-mcp
npm install

# 2) Build the project
npm run build

# 3) Start the MCP server via Claude Desktop config (see the JSON example for exact config values below)
# The runtime command for the local MCP server is the node process pointing to the built index.js
# Example runtime (used within Claude Desktop config):
# command: node
# args: ["/Users/you/path/to/df-mcp/build/index.js"]

# 4) Enable the MCP server in Claude Desktop extensions and restart Claude Desktop

Claude Desktop JSON configuration for the manual, local runtime (edit paths and URLs to fit your setup):

{
  "mcpServers": {
    "df-mcp": {
      "command": "node",
      "args": [
        "/Users/dreamfactory/Documents/df-mcp/build/index.js"
      ],
      "env": {
        "DREAMFACTORY_URL": "https://example.dreamfactory.com/api/v2/<service-name>",
        "DREAMFACTORY_API_KEY": ""
      }
    }
  }
}

Docker MCP Setup for Claude Desktop

You can run the DreamFactory MCP server in a Docker container and connect Claude Desktop to it. Build the image, then reference it in Claude Desktop’s MCP configuration.

Docker image build and configuration steps:

docker build -t df-mcp .

Claude Desktop configuration for the Docker-based MCP server (edit the paths and API values for your environment):

{
  "mcpServers": {
    "dreamfactory-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "--env", "DREAMFACTORY_URL=https://your-dreamfactory-instance.com/api/v2/<service-name>",
        "--env", "DREAMFACTORY_API_KEY=your-api-key-here",
        "dreamfactory-mcp:latest"
      ]
    }
  }
}

Testing and maintenance

After configuring either the local node-based MCP server or the Docker-based MCP server, restart Claude Desktop to load the MCP server. Use the Docker approach’s test script or the local Node-based server’s normal startup flow to ensure the server responds to MCP commands and that DreamFactory tools are registered correctly within Claude.

Security

Keep DreamFactory credentials secure by storing API keys in environment variables and avoiding hard-coded values in Claude Desktop configurations. Periodically rotate API keys and review access controls on your DreamFactory instance.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational