AgentMode + LibreChat: Complete MCP Integration

AgentMode is a MCP server that Connect to dozens of databases, data warehouses, Github & more, from a single MCP server. Run the Docker image locally, in the cloud, or on-premise..

When integrated with LibreChat, you can:

• Execute SQL queries across connected databases
• Interact with GitHub repositories and issues
• Connect to data warehouses like Snowflake, BigQuery

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

What You'll Achieve

After completing this setup:

• AgentMode will be fully integrated and operational
• You can use AgentMode tools directly in LibreChat
• All AgentMode capabilities will be available for your workflows
• Access to 3 different tools

Prerequisites

Before starting, ensure you have:

• API key from AgentMode dashboard
• Workspace identifier
• LibreChat installed and configured
• Compatible operating system (Docker (Recommended), Kubernetes, Local Installation, Cloud Platforms)

Installation

Step 1: Install AgentMode

Configuration

Step 2: Configure LibreChat

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

Examples

Once configured, you can use AgentMode in LibreChat:

Multi-Database Analytics

undefined

Ask LibreChat: "Show me user engagement metrics from both databases"

Expected Result: undefined

GitHub Issue Management

undefined

Ask LibreChat: "Create issues for users with failed payments"

Expected Result: undefined

Data Pipeline Monitoring

undefined

Ask LibreChat: "Check status of yesterday's data pipeline runs"

Expected Result: undefined

Testing Your Setup

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

Troubleshooting

Common Issues

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

AgentMode not appearing in LibreChat

Symptoms: Server not listed, Tools not available

Cause: Configuration or installation issue

Solution:

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

Next Steps

Now that AgentMode is integrated with LibreChat:

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

Need Help?

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