How to Use the Chainlit MCP in Mastra AI

Q: Can I make a Mastra AI agent that reacts to bad feedback in Chainlit?

Yes, that's a perfect use case. Your agent can use the listfeedbacks tool to find negative reviews. From there, you can define a workflow to fetch the conversation with getthread and escalate it by creating a JIRA ticket or sending a Slack alert.

Build unstoppable backend workflows for Chainlit with Mastra AI. Audit threads, check stats, and react to feedback automatically.

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 Mastra AI

Create your Vinkius account to connect Chainlit to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create Conditional Audit Workflows

Give your Mastra AI agent a list of rules for monitoring conversations. It can use `list_threads` to scan for new interactions and then apply your logic. For example, if a thread's metadata matches a certain pattern, the agent can automatically fetch the full context with `get_thread`. This is where Mastra's workflow engine shines. You can build a process that says, 'If `get_thread` fails, retry twice. If it still fails, send me a notification.' The agent handles the failure so your audit trail is always complete.

Automate Metric Reporting with this MCP Server

Stop pulling analytics manually. Set up a scheduled Mastra AI workflow to do it for you. The agent can use `list_projects` to get a current list of all your apps, then call `get_stats` for each one to collect traffic data. The agent assembles a report and sends it to Slack or email. If the Chainlit API is temporarily down during one of the calls, Mastra's built-in exponential backoff means the agent will just try again in a few moments. You get your report without any drama.

Build Feedback-Driven Response Systems

Don't let bad user experiences go unnoticed. A Mastra AI agent can periodically run `list_feedbacks` to check for low ratings. When it finds one, it triggers a workflow. That workflow could use the `get_thread` tool to pull the associated conversation, analyze it for root causes using `list_steps`, and then create a ticket in your issue tracker. This turns passive feedback into an active, automated quality assurance process.

Setup guide

Set up Chainlit MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Chainlit tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "chainlit-mcp-client",
  servers: {
    "chainlit-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Chainlit Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Chainlit tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Chainlit transactions"
);
console.log(result.text);

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 Mastra AI

Easily. Create a scheduled workflow in Mastra AI. Have the agent use the `list_projects` tool to get all your projects, then loop through them using `get_stats` to collect the numbers. It can then format and send the report.

Yes, that's a perfect use case. Your agent can use the `list_feedbacks` tool to find negative reviews. From there, you can define a workflow to fetch the conversation with `get_thread` and escalate it by creating a JIRA ticket or sending a Slack alert.

It's simple. After installing the Mastra MCP package, you instantiate the `MCPClient` with your Vinkius server URL. Then you call `mcpClient.listTools()` and spread the result into your agent's toolset. Mastra handles the rest.

No, auth is handled by the Vinkius platform. You get a single, secure URL endpoint with your token embedded. You pass that URL to Mastra AI, and all tool calls are automatically authenticated. It's a zero-config setup.

Only your agent. Access to your Chainlit conversation data and project stats is locked down by your private Vinkius token. The connection is point-to-point between your Mastra AI agent and the MCP server; your data isn't exposed elsewhere.

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