Getting Started
This guide will help you connect your AI client to BrightForest's MCP servers and start using domain-specific agent capabilities.
Prerequisites
- An MCP-compatible AI client (Claude Desktop, Continue.dev, or custom MCP client)
- A BrightForest account with API access
- Node.js 18+ (if using the Node.js MCP SDK)
Connection Methods
Option 1: Claude Desktop
Claude Desktop has built-in MCP support. Add BrightForest agents to your
claude_desktop_config.json:
Code
Configuration file locations: - macOS: ~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Option 2: Direct Connection
Connect directly to a BrightForest MCP server endpoint:
Code
Option 3: Custom Integration
Use the MCP SDK to integrate BrightForest agents into your own application:
Code
Authentication
All BrightForest MCP servers require authentication via API key. You can generate API keys from your BrightForest Dashboard.
Keep your API keys secure! Never commit them to version control or share them publicly. Use environment variables or secure credential storage.
Available MCP Servers
BrightForest provides MCP servers for each domain. Choose the ones relevant to your workflow:
| Domain | Server Name | Connection URL |
|---|---|---|
| Platform Integration | brightforest-platform | mcp://platform.brightforest.io |
| Enterprise Config | brightforestx-enterprise | mcp://enterprise.brightforestx.com |
| AI Orchestration | brightpath-orchestration | mcp://orchestration.brightpath.ai |
| Algorithm Optimization | pathx-optimization | mcp://optimization.pathx.ai |
| Design-to-Code | figmatofullstack-design | mcp://design.figmatofullstack.com |
| AI Design Assistant | figmatofullstack-ai | mcp://ai.figmatofullstack.ai |
| ML Platform | mlninjas-platform | mcp://platform.mlninjas.com |
| Portfolio Management | clifforddalsoniii-portfolio | mcp://portfolio.clifforddalsoniii.com |
| DIY AI Builder | getdiyai-builder | mcp://builder.getdiyai.com |
| RPA Workflows | getdiyrpa-workflows | mcp://workflows.getdiyrpa.com |
| App Builder | appnowhq-builder | mcp://builder.appnowhq.com |
| MLOps | brightforest-mlops | mcp://mlops.brightforest.ai |
| AI Learning | iheartai-learning | mcp://learning.iheartai.ai |
Coming Soon: All MCP servers are currently in development. Connection URLs are placeholders and will be activated as servers are released.
Testing Your Connection
Once configured, test your connection by querying available capabilities:
Code
Next Steps
Explore Agents
Learn about each specialized agent's capabilities
MCP Overview
Understand how BrightForest uses MCP
Troubleshooting
Connection Issues
- Verify your API key is valid and has the correct permissions
- Check that the MCP server path is correct
- Ensure Node.js version is 18 or higher
- Review logs in your MCP client's debug output
Permission Errors
- Confirm your API key has access to the requested agent domain
- Check your BrightForest plan includes the agent you're trying to use
- Contact support if you believe you should have access
Support
Need help? Reach out to us: