How to Use the ZenHub MCP in LlamaIndex

Q: Can I use ZenHub and LlamaIndex to query historical issue data?

Yes. Running getzenhubissuedata populates your index with specific metadata. You can then semantically search across multiple past sessions for that issue's history.

Q: How does LlamaIndex handle ZenHub board data?

You run tools like getrepoboard or getworkspaceboard, and the structured output is immediately chunked and indexed. This makes the raw board data searchable alongside your documents.

Q: Is ZenHub reliable for tracking estimates with LlamaIndex?

When you use setissueestimate, that action's outcome can be indexed. You can then query to ask, 'What was the story point estimate set for this issue after the last review?'

Q: Does ZenHub and LlamaIndex support tracking multiple epics?

Yes. By running listrepoepics and indexing those results, you can build a comprehensive knowledge graph of all high-level features associated with the repository.

Q: What data types are stored in the LlamaIndex for ZenHub?

This MCP server touches issue metadata (from getzenhubissuedata), epic details, board structures, and release report records. All these structured results become part of your searchable knowledge base.

Index ZenHub API data for semantic search using LlamaIndex.

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 LlamaIndex

Create your Vinkius account to connect ZenHub to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build RAG Applications with MCP Server

LlamaIndex indexes the results of your tool calls, making live data searchable. When you run `list_repo_epics`, the resulting list is stored in a vector index. Later, you can query that index to ask, 'Which epics were created last quarter?' and get an answer grounded in the API output. The capability extends to board management. Running `get_zenhub_issue_data` populates knowledge chunks about specific issues' metadata. Your RAG application then lets users search for historical issue context without having to know the exact ID.

Track Changes and Releases

Need to find out what was released? Use `list_release_reports` and index those reports immediately. Your knowledge base can then answer complex questions like, 'Show me all release reports that contained a change in the authentication pipeline.' Furthermore, if you use `move_issue_between_pipelines`, that action's context is indexed. This means future queries can track *why* an issue moved and *when* it was estimated.

Query Board History via MCP Server

You can index board data for deep historical questioning. After running `get_repo_board`, the structure of that board is added to your searchable knowledge base. You won't just get the current view; you'll get indexed context about its structure. It’s also useful for comparing views. Indexing results from both `get_repo_board` and `get_workspace_board` allows LlamaIndex to answer questions like, 'How did the general repository board differ from the specific workspace board last month?'

Setup guide

Set up ZenHub MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all ZenHub MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to ZenHub tools.",
)
response = await agent.run("List recent ZenHub data")

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 LlamaIndex

Yes. Running `get_zenhub_issue_data` populates your index with specific metadata. You can then semantically search across multiple past sessions for that issue's history.

You run tools like `get_repo_board` or `get_workspace_board`, and the structured output is immediately chunked and indexed. This makes the raw board data searchable alongside your documents.

When you use `set_issue_estimate`, that action's outcome can be indexed. You can then query to ask, 'What was the story point estimate set for this issue after the last review?'

Yes. By running `list_repo_epics` and indexing those results, you can build a comprehensive knowledge graph of all high-level features associated with the repository.

This MCP server touches issue metadata (from `get_zenhub_issue_data`), epic details, board structures, and release report records. All these structured results become part of your searchable knowledge base.

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