How to Use the ZenHub MCP in Mastra AI

Q: How do I use ZenHub with Mastra AI to get board data?

You integrate the getrepoboard tool into your workflow engine. Your agent can run this check, and if the returned board structure meets certain criteria, it triggers the next step in your process.

Q: Can Mastra AI manage ZenHub issue metadata?

Yes. You use getzenhubissuedata to pull specific details about a GitHub issue into your workflow. This data can then inform decisions, like determining if an estimate needs setting.

Q: What happens when ZenHub estimates are updated via Mastra AI?

You use setissueestimate to update the points. If this step is part of a complex workflow, Mastra AI ensures that if the API call fails (maybe due to permissions), it retries automatically before failing gracefully.

Q: How do I list ZenHub epics using Mastra AI?

The listrepoepics tool allows your workflow to fetch all active epics for a repository. This gives the agent a full scope of work that can be analyzed before proceeding with other tasks.

Automate complex project management workflows with Mastra AI and ZenHub.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ZenHub MCP to Mastra AI

Create your Vinkius account to connect ZenHub 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 ZenHub with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Change Issue Pipelines

When an issue needs a status bump, use `move_issue_between_pipelines` within your workflow. Your agent executes the move command, ensuring the ticket lands in the correct pipeline automatically. The system handles retries and confirmations if the initial attempt fails. This is key for complex state transitions. If moving the issue requires multiple steps or checks, Mastra AI manages that flow until it succeeds.

Fetch ZenHub Board Data

Need to analyze a board before triggering an action? Call `get_repo_board` to fetch the entire state of a repository's board. This data feeds into your multi-step workflow, allowing conditional branching based on what it finds. For instance, if the board shows certain columns are empty, the workflow can automatically notify an admin instead of proceeding.

Set Story Point Estimates

Use `set_issue_estimate` to programmatically assign or update story points for any issue. The agent takes the issue ID and the new estimate, executing the change as part of a larger process. This is great for audit trails. You can build a workflow that validates estimates against team capacity before committing the change.

Setup guide

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

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

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

You integrate the `get_repo_board` tool into your workflow engine. Your agent can run this check, and if the returned board structure meets certain criteria, it triggers the next step in your process.

Yes. You use `get_zenhub_issue_data` to pull specific details about a GitHub issue into your workflow. This data can then inform decisions, like determining if an estimate needs setting.

You use `set_issue_estimate` to update the points. If this step is part of a complex workflow, Mastra AI ensures that if the API call fails (maybe due to permissions), it retries automatically before failing gracefully.

The `list_repo_epics` tool allows your workflow to fetch all active epics for a repository. This gives the agent a full scope of work that can be analyzed before proceeding with other tasks.

This server touches story point estimates and general board metadata. It specifically handles `set_issue_estimate`, which modifies the story point value for an issue, requiring careful access control in your workflow.

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