How to Use the Linear (Issue Tracking & PM) MCP in LangChain

Q: Can LangChain chain multiple Linear (Issue Tracking & PM) tools together?

Yes, that is how this setup works best. Your agent can run listissues to find untagged bugs, then immediately call listlabels to find the right tag and apply it.

Q: How does LangChain handle sprint cycles using this Linear (Issue Tracking & PM) integration?

The agent calls listcycles to pull your active sprint boundaries. It compares this data with your backlog to ensure you do not over-commit during planning.

Build multi-step PM chains that query issues and assign cycles in LangChain using this Linear MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Linear (Issue Tracking & PM) MCP to LangChain

Create your Vinkius account to connect Linear (Issue Tracking & PM) 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 Linear (Issue Tracking & PM) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-step issue triage in LangChain

The `list_issues` tool fetches your recent workspace tickets so your LangChain agent can analyze incoming backlog volume. It inspects titles and descriptions, then passes that data directly to the next step in your chain without manual copying. This setup lets you build autonomous triage loops. Your agent checks the active user boundaries with `get_viewer`, matches the tickets, and decides which team gets the work based on live API data.

Map sprint cycles directly inside your chains

The `list_cycles` tool exposes active sprint boundaries to your LangChain agent for immediate execution planning. The agent evaluates current team velocity and matches it against open tickets to prevent sprint overflow during high-stress releases. You can feed this cycle data into LangSmith to trace how your agent schedules tasks. By combining this with `list_projects`, your pipeline gets a clear view of where resources are actually going.

Audit team assignments with this MCP Server

The `list_teams` tool queries your workspace structure to help your agent assign incoming tickets to the correct group. It prevents misrouted tasks by matching team boundaries with the labels retrieved via `list_labels`. Instead of guessing who owns a project, your LangChain chain uses `list_users` to find active team members. The agent then routes the work to the right person, keeping your workspace clean and updated.

Setup guide

Set up Linear (Issue Tracking & PM) 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 Linear (Issue Tracking & PM) 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({
    "linear-issue-tracking-pm-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 Linear (Issue Tracking & PM) 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 Linear. 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 Linear (Issue Tracking & PM) 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 Linear (Issue Tracking & PM) MCP in LangChain

You install the MCP adapter package and initialize the client with your Vinkius endpoint. From there, you call get_tools to pass the Linear tools directly to your agent constructor.

Yes, that is how this setup works best. Your agent can run `list_issues` to find untagged bugs, then immediately call `list_labels` to find the right tag and apply it.

The agent calls `list_cycles` to pull your active sprint boundaries. It compares this data with your backlog to ensure you do not over-commit during planning.

Use LangSmith to trace the exact inputs and outputs of every tool call. You will see exactly what `get_issue` returned and how your agent used that data to make decisions.

Your data stays inside the secure Vinkius V8 sandbox. The server only touches your Linear issues, cycle bounds, and user mappings to execute your specific tool requests, and we never store your API keys or backlog content.

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