How to Use the GPTBots MCP in Mastra AI

Q: How do I register GPTBots tools inside a Mastra AI agent?

Install @mastra/mcp@latest and initialize the client using the MCP Server URL. Next, call mcpClient.listTools() and spread those tools directly into your agent configuration array. The framework automatically configures the SSE or HTTP transport.

Q: Can I inspect past GPTBots chat logs inside my Mastra AI agent?

Yes, your agent can call listconversations to find active sessions. From there, use getconversation to fetch the exact message history, allowing your agent to reconstruct context across different execution runs.

Q: How do I send messages to my remote agents?

Use sendbotmessage within your agent's tool execution block. This routes the prompt directly to the remote platform, returning the response as structured data that your Mastra agent can parse and act on using the MCP protocol.

Q: How does the GPTBots integration secure my document uploads?

All files uploaded via createknowledgedocument are encrypted in transit and stored in your isolated workspace. Vinkius handles the authorization tokens, meaning your local Mastra runtime never exposes raw API keys to the public internet.

Build resilient, multi-step agent workflows that trigger and monitor GPTBots tasks using Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GPTBots MCP to Mastra AI

Create your Vinkius account to connect GPTBots 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 GPTBots with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate multi-step workflow executions with retries

`trigger_workflow` starts complex background processes that run asynchronously from your main agent loop. Mastra handles the execution lifecycle, retrying the call with exponential backoff if the external service experiences a temporary outage. You can check the execution status at any point by calling `query_workflow`. This keeps your agent informed of background progress, allowing it to branch into error-recovery steps if a workflow fails to complete.

Secure your database using Mastra AI and MCP Server tools

`list_databases` reads your system table structures so your agent can plan its next data operations. Mastra lets you guard this tool with `requireToolApproval` to force a human review before any schema details are exposed. This human-in-the-loop step prevents unauthorized schema exploration during autonomous runs. Your agent waits for the admin's green light in the console before executing the database discovery tool over MCP.

Sync agent memory with remote document stores

`create_knowledge_document` pushes raw text and files directly into your remote vector knowledge bases. Your agent can dynamically write new context files during a run, updating its own reference materials. To check the update, `list_knowledge_documents` inspects the active document library. Mastra workflows can run this check sequentially to ensure the new context is indexed before proceeding to the next decision step.

Setup guide

Set up GPTBots 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 GPTBots 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: "gptbots-mcp-client",
  servers: {
    "gptbots-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent GPTBots 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 GPTBots. 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 GPTBots 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 GPTBots MCP in Mastra AI

Install `@mastra/mcp@latest` and initialize the client using the MCP Server URL. Next, call `mcpClient.listTools()` and spread those tools directly into your agent configuration array. The framework automatically configures the SSE or HTTP transport.

Use Mastra's built-in workflow engine to wrap your calls to `trigger_workflow`. If the initial trigger fails, the workflow engine automatically retries the operation based on your backoff settings before invoking `query_workflow`.

Yes, your agent can call `list_conversations` to find active sessions. From there, use `get_conversation` to fetch the exact message history, allowing your agent to reconstruct context across different execution runs.

Use `send_bot_message` within your agent's tool execution block. This routes the prompt directly to the remote platform, returning the response as structured data that your Mastra agent can parse and act on using the MCP protocol.

All files uploaded via `create_knowledge_document` are encrypted in transit and stored in your isolated workspace. Vinkius handles the authorization tokens, meaning your local Mastra runtime never exposes raw API keys to the public internet.

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