- CONTEXT
- MODELS
- CHAT
- HUMAN
Short answer
How can I bring my LibreChat agents into Cursor or VS Code?
Connect the LibreChat MCP to your editor to make your custom agents available to your AI client. You'll be able to pick from your existing agent configurations to guide your coding sessions.
The outcomes
Where your work lands
Your agents move from the web interface to your local development environment.
CONTEXT
Agents in your editor
Your AI client pulls in the instructions and settings from LibreChat. This means your specific coding personas are ready to go in Cursor or VS Code.
MODELS
Model availability
The agent can see which models are available through the connection. You can choose the right model for the specific task at hand.
CHAT
Direct interaction
You send messages to your agents through your IDE's chat interface. The agent responds using the logic you already set up in LibreChat.
HUMAN
You stay in control
The AI handles the agent logic, but you decide when to apply a specific agent to a file or a block of code. It won't change your agent settings without you.
The workflow
What your AI does when the connection is live.
The MCP acts as a bridge between your LibreChat configuration and your coding environment.
Fetch agent list
Your AI client looks at your LibreChat setup to see which agents you have created. It identifies the available personas for your current session.
list_modelsSelect a model
The agent checks which models are compatible with your request. It ensures the conversation uses the right engine for the job.
list_modelschat_completionsExecute chat
When you ask a question, the agent uses the specific instructions from your LibreChat agent. It processes your prompt through the selected model.
chat_completionsDeliver code
The agent sends the completed response back to your IDE. You get the code or explanation directly in your chat window.
chat_completions
Try it
Copy these to start.
Use these prompts to trigger your agents in the IDE.
Starting points
These are ideas to get you moving. Swap out the agent names for the ones you actually created in LibreChat.
LibreChat Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_2Y5OcBZjfHKkJsGbCGI3uDOzGTusTgIZgBtbs3a3/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — LibreChat capabilities are ready to use.
{
"mcpServers": {
"librechat-mcp": {
"url": "https://edge.vinkius.com/vk_preview_2Y5OcBZjfHKkJsGbCGI3uDOzGTusTgIZgBtbs3a3/mcp"
}
}
}Use my 'Python Expert' agent to refactor this function.
Switch to my 'Frontend Architect' agent and review this CSS.
Using my 'Documentation Bot' agent, write a README for this folder.
Apply my 'Security Auditor' agent to check this file for vulnerabilities.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect LibreChat once, then ask.
Click the link to connect your account. Your credentials stay encrypted, and you can find the full setup details on the Connector page.
Connect LibreChat to your AIFAQ
How the connection behaves
- 01
Can the AI change my LibreChat agent settings?
No. The AI can only read the agent configurations to use them. It cannot modify your settings in LibreChat.
- 02
Do I have to manually copy my prompts from LibreChat?
No. Once connected, your AI client can access the agents directly through the MCP.
- 03
Will this work in Windsurf?
Yes, any MCP-compatible client like Windsurf, Cursor, or VS Code will work.
- 04
Can the AI delete my agents?
No. The available tools only allow for listing models and sending chat completions. There is no tool to delete or edit agents.
- 05
Does this work with any model?
It works with any model that your LibreChat instance provides through the connection.
More questions about LibreChat? See everything the LibreChat Connector can do
Connect LibreChat to Claude, Cursor, ChatGPT & more
