How to Use the Chainlit MCP in Cursor

Inject live Chainlit observability metrics and chat threads directly into your codebase using Cursor.

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 Cursor

Create your Vinkius account to connect Chainlit to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chainlit MCP Server for Live Context

Running `get_thread` lets Cursor pull the exact payload for a specific conversational thread into your editor. Agent mode reads the node topologies while you write evaluation scripts. Mock data wastes time when you need to test LLM observability pipelines. The AI fetches raw programmatic interaction steps via `list_steps` and writes code based on actual prompt generations.

Analyze Feedbacks Mid-Coding

Cursor calls `list_feedbacks` to retrieve absolute user review ratings across your deployments. You can write custom dashboards while the AI references conversational accuracy and value scores. Developers building feedback loops need real user data. Invoking `list_threads` identifies user interaction boundaries inside a specific deployed project, letting the agent structure your data models accurately.

Query Project Statistics Automatically

Fetching explicit analytics statistics representing traffic boundaries requires calling `get_stats`. Your editor grabs resource consumption data over native projects without forcing you to switch windows. Setting up automated MCP reporting scripts becomes trivial. The AI uses `list_projects` to list globally configured Chainlit Cloud projects, then writes the exact API calls you need to manage independent app tracking spaces.

Setup guide

Set up Chainlit MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Chainlit MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Chainlit transactions." If the MCP tools are loaded correctly, Cursor will call the Chainlit tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

Create an configuration file in your project root or global directory. Add the Vinkius endpoint URL under the server settings and enable Agent mode.

The agent pulls live prompts and generations using the steps tool. It then generates test scripts based on the actual model outputs from your deployed projects.

You ask the AI to invoke the feedback list. It retrieves the conversational accuracy ratings and uses that live data to help you build analytics components.

Placing the MCP configuration file in your global directory makes the tools available everywhere. You can access project statistics and thread payloads from any local repository.

Zero-trust architecture isolates your conversational threads from other users. The managed infrastructure executes your queries in temporary environments, keeping your LLM observability metrics strictly confidential.

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