How to Use the ChatFly MCP in Cursor

Q: How does the ChatFly MCP Server work with Cursor's agent?

Once you configure it in your mcp.json file, Cursor's agent can invoke any ChatFly tool. You can ask it to createbot or listbots, and it will perform the action and use the output in its response or code generation.

Q: Can I manage multiple ChatFly bots from Cursor?

Yes. The listbots tool gives your agent a full inventory of your bots. You can then instruct it to perform actions like updatebot or getbot on any specific bot by name or ID.

Q: How do I add a knowledge base to a ChatFly bot from within Cursor?

You tell the agent to use the uploaddatasource tool, providing the path to your knowledge base file. The agent will handle the upload, and the bot will start training on that new information.

Generate code that interacts with your AI chatbots. Build and test support bots without leaving the Cursor editor.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChatFly MCP to Cursor

Create your Vinkius account to connect ChatFly 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 ChatFly with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Chatbot Logic with Live Data

Use Cursor's agent to call ChatFly tools and get real data back. Instead of writing boilerplate to create a bot, just ask the agent: "Create a new chatbot named 'Lead Gen Bot'." It will run the `create_bot` tool and show you the result. This changes how you build integrations. The agent can use `get_bot` to fetch a real bot's ID, then generate the exact code you need to interact with it, complete with the correct identifiers. No more placeholder values or switching contexts to look up IDs.

Script Your Chatbot Setup with this MCP Server

You can script the entire lifecycle of a chatbot from a single chat prompt in Cursor. Tell the agent to create a bot, upload a data source using `upload_data_source`, and then update its welcome message with `update_bot`. It executes the commands in sequence. This is perfect for creating reproducible setups for different environments, like dev and staging. You see the output of each step and can even ask the agent to write a script that automates the whole process.

Test Bot Interactions in Your Editor

The `chat` tool lets your agent talk directly to any of your chatbots. You can write a test case in a comment, and the agent will execute it against the live bot and return the actual response, right in your editor. This makes debugging conversational flows incredibly fast. If a bot gives a weird answer, you can immediately check its configuration with `get_bot` or `list_data_sources` right there, fix the data, and re-run the test.

Setup guide

Set up ChatFly 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 ChatFly 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 ChatFly transactions." If the MCP tools are loaded correctly, Cursor will call the ChatFly tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "chatfly-alternative-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 ChatFly. 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 ChatFly 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 ChatFly MCP in Cursor

Once you configure it in your `mcp.json` file, Cursor's agent can invoke any ChatFly tool. You can ask it to `create_bot` or `list_bots`, and it will perform the action and use the output in its response or code generation.

Yes. The `list_bots` tool gives your agent a full inventory of your bots. You can then instruct it to perform actions like `update_bot` or `get_bot` on any specific bot by name or ID.

Absolutely. You can use ChatFly tools within Cursor to get a bot's ID, then ask the agent to write the frontend JavaScript code needed to connect to that specific bot's endpoint.

You tell the agent to use the `upload_data_source` tool, providing the path to your knowledge base file. The agent will handle the upload, and the bot will start training on that new information.

ChatFly is sandboxed and only interacts with the data its tools need to function: bot configurations like names and welcome messages, plus the knowledge source files you explicitly upload. Vinkius isolates the entire process, so your code and local environment are never exposed to the server.

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