How to Use the Chainlit MCP in VS Code Copilot

Give your engineering team direct access to Chainlit chat threads and model steps inside VS Code Copilot.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chainlit MCP to VS Code Copilot

Create your Vinkius account to connect Chainlit to VS Code Copilot and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Chainlit with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Team-Wide Chainlit MCP Server Access

Committing a configuration file lets everyone on your team call `list_projects` to view globally configured Chainlit Cloud projects. Copilot reads independent app tracking spaces directly from the repository configuration. Engineers stop begging for dashboard access. The AI invokes `get_stats` to retrieve explicit analytics statistics representing traffic boundaries and resource consumption over native projects.

Audit Conversational Threads in the Editor

Troubleshooting model behavior starts by running `get_thread` to fetch the exact payload for a specific conversational thread. Your agent locates exact node topologies without leaving the IDE. Debugging requires looking at the raw inputs and outputs. Calling `list_steps` lists raw programmatic interaction steps, defining prompts and generations inside a single thread so you can fix hallucination issues fast.

Track User Feedback Across Deployments

Copilot uses `list_feedbacks` to list absolute user review ratings regarding conversational accuracy and value. You get real metrics from production deployments right next to your code. Understanding user behavior helps you tune your prompts. Running `list_threads` identifies user interaction boundaries inside a specific deployed project, giving your team the context needed to improve model performance.

Setup guide

Set up Chainlit MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Chainlit MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Chainlit tools listed. Try asking: "List my recent Chainlit transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "chainlit-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Chainlit. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Chainlit now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Chainlit MCP in VS Code Copilot

You create a settings file in your project root and commit it to Git. Every developer who pulls the repository gets immediate access to the observability tools.

Calling the thread tool retrieves the exact payload for any conversation. The MCP agent reads the node topologies and helps you debug model responses directly in your editor.

The AI fetches explicit analytics statistics using the stats tool. You can view traffic boundaries and resource consumption over your native projects without opening a browser.

Yes, the MCP agent mode features rely on the latest extension updates. You need a recent build to let the AI interact with your deployed projects.

Enterprise-grade isolation protects your raw programmatic interaction steps. Vinkius processes every request in a sandboxed V8 environment that destroys itself after executing the tool, ensuring your user feedback data remains private.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript