Connect your AI coding agent to ModelsLab’s account management capabilities. The Agent Control Plane MCP server is hosted — no installation required. Just add the URL and your bearer token.Documentation Index
Fetch the complete documentation index at: https://docs.modelslab.com/llms.txt
Use this file to discover all available pages before exploring further.
Overview
The Agent Control Plane MCP server works with any client that supports the Model Context Protocol over HTTP:- Claude Code - Anthropic’s CLI coding assistant
- Claude Desktop - Claude’s desktop application
- Cursor - AI-powered code editor
- VS Code - Via GitHub Copilot agent mode
- Windsurf - Codeium’s AI editor
- OpenCode - Open-source AI coding agent
- Continue - Open-source AI code assistant
Unlike the Generation MCP server which uses API keys, the Agent Control Plane uses Sanctum bearer tokens. Get a token by calling the
agent-auth tool with the login action, or via the REST API.Getting Your Bearer Token
Before configuring your IDE, get a bearer token:access_token from the response.
Using Both MCP Servers Together
For full ModelsLab access, configure both MCP servers:| Server | URL | Auth | Purpose |
|---|---|---|---|
| Generation | https://modelslab.com/mcp/v7 | API key | Image, video, audio, LLM generation |
| Agent Control Plane | https://modelslab.com/mcp/agents | Bearer token | Account, billing, subscriptions, teams |
Claude Code
- macOS / Linux
- Windows
Edit
~/.claude/settings.json:settings.json
Usage
Claude Desktop
- macOS
- Windows
Edit
~/Library/Application Support/Claude/claude_desktop_config.json:claude_desktop_config.json
Cursor
Add to your Cursor MCP settings or edit.cursor/mcp.json in your project:
mcp.json
VS Code (Copilot Agent Mode)
Edit.vscode/mcp.json in your workspace:
mcp.json
Windsurf
Edit~/.codeium/windsurf/mcp_config.json:
mcp_config.json
OpenCode
- Project-level
- Global
Edit
opencode.json in your project root:opencode.json
Continue
Edit~/.continue/config.json:
config.json
Generic MCP Client
For any MCP-compatible client:Environment Variables
For security, use environment variables instead of hardcoding tokens:- macOS / Linux
- Windows
Add to your shell profile (Then reference in config:
~/.bashrc, ~/.zshrc):Verification
After configuring, verify the integration:Test Connection
Ask your AI agent:Test Model Discovery
Check for Errors
If the integration is not working, check:- Token: Ensure your bearer token is valid and not expired
- URL: Verify the endpoint is
https://modelslab.com/mcp/agents - Headers: Confirm the
Authorization: Bearerformat - Client support: Ensure your MCP client supports HTTP/SSE transport
Troubleshooting
401 Unauthorized errors
401 Unauthorized errors
Tools not appearing
Tools not appearing
- Restart your MCP client after configuration changes
- Check the configuration file syntax (valid JSON)
- Verify the config file is in the correct location
Connection timeout
Connection timeout
- Verify the endpoint URL is correct
- Check your network connection and firewall rules
Difference between API key and bearer token
Difference between API key and bearer token
- API key: Used for generation endpoints (
/mcp/v7). Get from dashboard oragent-api-keystool - Bearer token: Used for control plane (
/mcp/agents). Get fromagent-authlogin
Next Steps
Tools Reference
Complete documentation for all 10 control plane tools
Agents REST API
Direct REST API documentation for the control plane

