How to Use the Beekeeper MCP in Mastra AI

Q: Can a Mastra AI agent manage Beekeeper user groups automatically?

Absolutely. The agent can use listgroups to get all available groups and then use that information to perform other actions, like adding users to specific streams associated with those groups.

Q: How does Mastra AI handle failures when posting to a Beekeeper stream?

Mastra AI has built-in retry logic. If a createpost call fails, the framework can automatically retry it. You can configure the number of retries and backoff strategy for critical operations.

Q: What's the best way to get started with the Beekeeper MCP and Mastra AI?

Install the @mastra/mcp package. Then, instantiate the MCPClient with your Vinkius server URL and pass the tools from listTools() to your agent configuration. Mastra handles the transport details for you.

Q: Can I require human approval before a Mastra AI agent sends a message in Beekeeper?

Yes, Mastra AI supports requireToolApproval. You can configure your agent to pause and wait for a human to confirm before executing sensitive tools like sendmessage or createpost.

Build failure-proof Beekeeper automations with Mastra AI. Onboard users, moderate content, and manage streams with conditional workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Beekeeper MCP to Mastra AI

Create your Vinkius account to connect Beekeeper 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 Beekeeper with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Beekeeper Onboarding

This toolset lets you build a complete user onboarding workflow. When a new employee is added to your HR system, a Mastra agent can trigger a sequence: `search_users` to see if they exist, then `get_tenant_info` to check settings, and finally add them to the right groups. With Mastra's workflow engine, you can add conditional logic. For example, if the user is in the 'Engineering' department, add them to the 'dev-updates' stream using their group ID from `list_groups`. It's all automated.

Run Resilient Beekeeper Workflows with Mastra AI

Send critical announcements or messages without worrying about transient network issues. Use `create_post` or `send_message` inside a Mastra workflow, and it will automatically handle retries with exponential backoff if the initial attempt fails. You can build a workflow that attempts to post an urgent update to a stream. If it fails after three retries, the agent can then use `send_message` to notify an admin directly. This MCP server provides the actions; Mastra provides the guarantees.

Sync User Data Across Systems

Keep your internal database or CRM in sync with Beekeeper. A recurring Mastra job can `list_users` and compare the list against your own records, flagging discrepancies for review. You can also build reporting workflows. For instance, an agent could run `list_posts` on a specific stream daily, count the number of posts, and send a summary report to a manager using the `send_message` tool. It's a hands-off way to monitor activity.

Setup guide

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

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

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

Absolutely. The agent can use `list_groups` to get all available groups and then use that information to perform other actions, like adding users to specific streams associated with those groups.

Mastra AI has built-in retry logic. If a `create_post` call fails, the framework can automatically retry it. You can configure the number of retries and backoff strategy for critical operations.

Install the `@mastra/mcp` package. Then, instantiate the `MCPClient` with your Vinkius server URL and pass the tools from `listTools()` to your agent configuration. Mastra handles the transport details for you.

Yes, Mastra AI supports `requireToolApproval`. You can configure your agent to pause and wait for a human to confirm before executing sensitive tools like `send_message` or `create_post`.

The server processes only the data needed for the specific tool call, such as user lists, stream content, or private message text. Each transaction is handled within a zero-trust, ephemeral Vinkius sandbox, and no user or message data is logged or retained.

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