How to Use the ZenHub MCP in LangChain

Q: Can I use ZenHub and LangChain to calculate story point estimates?

Absolutely. You can first pull issue details with getzenhubissuedata. Then, the agent uses that context to call setissueestimate directly on the issue record.

Q: What happens if I need to know about ZenHub board status in LangChain?

You can compare results from both boards. Use getrepoboard for a general view, and then use getworkspaceboard for a specific project area. This comparison is great for validating process compliance.

Q: Where is the most accurate data source for ZenHub board information in LangChain?

The server offers two endpoints: getrepoboard and getworkspaceboard. You should use both to validate which view aligns best with your required business process.

Build multi-step workflows for ZenHub using LangChain.

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 LangChain

Create your Vinkius account to connect ZenHub to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Orchestrate Workflow Logic with MCP Server

Your agent can construct complex project management chains. For instance, it first calls `list_repo_epics` to gather all high-level features; then, based on the results, it decides which specific board data is needed by calling `get_workspace_board`. This sequential execution lets you build true reasoning pipelines. The output of one function call becomes the input for the next tool. You can use this pattern to set up estimates: first getting issue metadata with `get_zenhub_issue_data`, and then immediately setting a point estimate using `set_issue_estimate`.

Manage Issue Status Changes

Need to move an issue? The agent handles the state change logic. It first fetches all available epics via `list_repo_epics`. Then, it uses that data structure to execute `move_issue_between_pipelines`, ensuring the issue lands in the correct next stage of development. This is critical for automated reporting. If a release report needs updating, your agent can list reports using `list_release_reports` before moving an issue and making sure all necessary records are updated.

Fetch Detailed Board Data

The MCP Server provides two ways to view board data. You can get the general board for a repository with `get_repo_board`, or you can narrow it down by specific workspace and repo using `get_workspace_board`. This distinction lets your agent target exactly where the issue lives. When building an observability chain, your agent needs accurate inputs. It uses tools like `get_epic_data` to pull core data, which feeds into subsequent steps that might validate or update records.

Setup guide

Set up ZenHub MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes ZenHub tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "zenhub-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent ZenHub transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Your agent can create chains of actions. You can list all epics using `list_repo_epics`, then select a specific epic's data via `get_epic_data`. This allows the agent to build a complete picture before making any changes.

Absolutely. You can first pull issue details with `get_zenhub_issue_data`. Then, the agent uses that context to call `set_issue_estimate` directly on the issue record.

You can compare results from both boards. Use `get_repo_board` for a general view, and then use `get_workspace_board` for a specific project area. This comparison is great for validating process compliance.

Yes. Besides boards and epics, you can pull release report lists using `list_release_reports`. Your agent can combine this with issue movement to track full product lifecycle changes.

The server offers two endpoints: `get_repo_board` and `get_workspace_board`. You should use both to validate which view aligns best with your required business process.

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