AgentBay + LibreChat: Complete MCP Integration

AgentBay is a MCP server that An MCP server for providing serverless cloud infrastructure for AI agents..

When integrated with LibreChat, you can:

• One-click environment session management with automatic scaling
• Web browser access and automation within cloud environments
• File management and manipulation in cloud environments

This guide provides step-by-step instructions to set up AgentBay in LibreChat, including configuration, examples, and troubleshooting.

What You'll Achieve

After completing this setup:

• AgentBay will be fully integrated and operational
• You can use AgentBay tools directly in LibreChat
• All AgentBay capabilities will be available for your workflows
• Access to 5 different tools

Prerequisites

Before starting, ensure you have:

• LibreChat installed and configured
• Compatible operating system (Docker (Recommended), Kubernetes, Local Installation, Cloud Platforms)

Installation

Step 1: Install AgentBay

Configuration

Step 2: Configure LibreChat

1. Open LibreChat settings
2. Navigate to MCP server configuration
3. Add AgentBay server with appropriate settings
4. Save and restart if needed

Examples

Once configured, you can use AgentBay in LibreChat:

Open Browser Session

Launch browser and navigate to specific website

Ask LibreChat: "Open browser with wuying-agentbay and access wuying.aliyun.com"

Expected Result: Browser session started with navigation to specified URL and screen streaming enabled

Development Environment Setup

Create isolated development environment for coding project

Ask LibreChat: "Set up a Python development environment with required packages for data analysis"

Expected Result: Linux environment created with Python, pip, and data analysis libraries installed

File Processing Workflow

Upload, process, and download files using cloud resources

Ask LibreChat: "Upload my dataset.csv, run data processing script, and download the results"

Expected Result: File uploaded, processing completed in cloud environment, results available for download

Multi-Agent Deployment

Deploy multiple AI agents for parallel processing

Ask LibreChat: "Deploy 5 AI agents for parallel image processing tasks with load balancing"

Expected Result: Multiple agent instances deployed, work distributed, and results aggregated

Testing Your Setup

1. Launch LibreChat
2. Verify AgentBay is available in the tools list
3. Test basic AgentBay functionality

Troubleshooting

Common Issues

API Key Authentication Failed

Symptoms: Access denied errors, Invalid API key messages, 401 Unauthorized

Cause: Invalid or expired API key

Solution:

• Verify API key is correct and active in AgentBay Console
• Check API key permissions and quotas
• Regenerate API key if expired or compromised
• Ensure API key is properly URL-encoded in SSE endpoint

Concurrent Instance Limit Exceeded

Symptoms: Resource allocation errors, Instance creation failures

Cause: Public beta limit of 10 concurrent instances reached

Solution:

• Wait for existing instances to complete or terminate them
• Optimize workflows to use fewer concurrent instances
• Consider upgrading to production plan for higher limits
• Monitor instance usage and implement resource pooling

Environment Session Lost

Symptoms: Session disconnection, State not persisted, Data loss

Cause: Network connectivity issues or session timeout

Solution:

• Use EXTERNALID parameter for persistent sessions
• Implement session restoration mechanisms
• Save work frequently to persistent storage
• Check network stability and connection quality

Screen Streaming Performance Issues

Symptoms: Lag in browser streaming, Poor video quality, Connection drops

Cause: Network bandwidth limitations or high latency

Solution:

• Check internet connection speed and stability
• Use lower quality settings for better performance
• Choose nearest edge location for better latency
• Optimize browser usage for streaming performance

MCP Server Not Connecting

Symptoms: Status shows "Disconnected" or "Error", Server not appearing in list, Connection timeout

Cause: Invalid configuration, missing dependencies, or server startup failure

Solution:

• Check librechat.yaml syntax is valid YAML
• Verify npx and Node.js are available (for stdio/command-based servers)
• Check server command and args are correct
• Review LibreChat logs for error messages: docker logs librechat
• Increase timeout value if server takes longer to initialize
• Ensure required ports are not blocked (for HTTP-based servers)

OAuth Authentication Failing

Symptoms: Status shows "OAuth Required", Redirect loop during auth, Token refresh errors

Cause: OAuth credentials not configured or redirect URLs incorrect

Solution:

• Verify OAuth clientId and clientSecret in librechat.yaml
• Check redirect URL is correctly set in OAuth provider settings
• Ensure authorizationUrl and tokenUrl are accessible
• Complete OAuth flow by clicking "Initialize" in MCP Settings panel
• Check browser console for OAuth-related errors

User Credentials Not Working

Symptoms: Prompts for credentials not appearing, Variables not substituted, Authentication errors

Cause: User credential variables incorrectly formatted or not entered

Solution:

• Use correct format: {{USER_VARIABLE_NAME}} in librechat.yaml
• Enter credentials through MCP Settings panel in UI
• Verify variable names match between config and UI
• Check credentials are saved per-user (not shared globally)

Tools Not Appearing in Chat

Symptoms: No tool dropdown available, MCP tools missing from interface, Server connected but tools unavailable

Cause: MCP server not properly integrated with chat endpoint or agent

Solution:

• Verify you are using an endpoint that supports MCP (not all models do)
• Check if Agent Builder is enabled and MCP tools are assigned to agent
• Restart chat session after adding new MCP servers
• Verify MCP server actually provides tools (some servers are resource-only)
• Check server logs to confirm tools are being discovered

Docker Deployment Problems

Symptoms: Container fails to start, Database connection errors, Port conflicts

Cause: Docker configuration issues or missing environment variables

Solution:

• Verify .env file is properly configured with all required variables
• Check MongoDB connection string is correct
• Ensure ports 3080 (frontend) and 3081 (backend) are available
• Run docker compose logs to view detailed error messages
• Verify Docker and Docker Compose versions meet minimum requirements

Performance Issues with MCP

Symptoms: Slow tool execution, Timeout errors, UI freezing during tool calls

Cause: Server timeout too short, inefficient MCP server, or network latency

Solution:

• Increase timeout values in librechat.yaml (both init and operation timeouts)
• Use HTTP transport instead of stdio for remote servers
• Monitor MCP server performance independently
• Consider caching for frequently accessed resources
• Use Streamable HTTP transport for production environments

AgentBay not appearing in LibreChat

Symptoms: Server not listed, Tools not available

Cause: Configuration or installation issue

Solution:

• Verify configuration syntax
• Check AgentBay installation
• Restart LibreChat
• Check logs for error messages

Next Steps

Now that AgentBay is integrated with LibreChat:

• Explore all AgentBay capabilities through LibreChat
• Check out other MCP servers that work with LibreChat
• Join the MCP community for tips and support
• Consider contributing to AgentBay development

Need Help?

• Search for AgentBay documentation
• Check the LibreChat MCP guide
• Join the MCP community discussions