How to Use the Linear MCP in CrewAI

Q: How do I restrict a CrewAI agent to only read Linear issues?

You use the MCPServerHTTP class from crewai.mcp and apply a toolfilter. This lets you expose read-only tools like listissues while blocking write tools like updateissue for sensitive agents.

Q: What format does the comment tool support?

The createcomment tool supports standard Linear Markdown. Your agents can write comments containing bold text, bullet points, strikethroughs, and user @mentions directly.

Deploy a multi-agent crew using the Linear MCP Server to coordinate issue triage, project planning, and cycle updates autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Linear MCP to CrewAI

Create your Vinkius account to connect Linear to CrewAI 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 with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Triage with the Linear MCP Server

`list_issues` lets your CrewAI triage agents pull unassigned tickets from your backlog to analyze their urgency. A researcher agent can scan the description, while an analyzer agent determines the correct priority and component labels. Once analyzed, a coordinator agent uses `update_issue` to assign the ticket to the right engineer and set the priority field. This multi-agent collaboration runs entirely through the Vinkius MCP Server, keeping your backlog clean without manual review.

Autonomous Project Status Monitoring

`get_project` retrieves deep metadata about active milestones, allowing your CrewAI planning agents to track team velocity. The agents evaluate project deliverables and compare them against active ticket states across your workspace. When an agent detects a blocked milestone, it uses `create_comment` to flag the blockers on the parent ticket. This proactive communication ensures your engineering managers get immediate visibility into project delays.

Automated Sprint Planning and Cycle Updates

`list_cycles` exposes active sprint dates and completion percentages to your CrewAI management agents. Your crew uses this data to decide which rollover issues need to be pushed to the next cycle. By combining `list_labels` and `search_issues`, the agents find high-priority tickets that missed the current sprint. They then update those issues automatically, ensuring your sprint metrics remain accurate and up to date.

Setup guide

Set up Linear MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Linear tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Linear Analyst",
    goal="Access and analyze Linear data via MCP.",
    backstory="Expert analyst with direct Linear access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Linear transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Linear Analyst",
        goal="Access and analyze Linear data via MCP.",
        backstory="Expert analyst with direct Linear access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Linear transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 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 MCP in CrewAI

You pass the Vinkius HTTP endpoint URL directly into the agent's `mcps` array during initialization. This grants that specific CrewAI agent access to tools like `search_issues` and `create_comment` while restricting others.

Yes, CrewAI agents can run tasks in parallel, calling tools like `get_issue` or `list_teams` simultaneously. The managed Vinkius backend handles this concurrent traffic, ensuring stable API performance.

You use the `MCPServerHTTP` class from `crewai.mcp` and apply a `tool_filter`. This lets you expose read-only tools like `list_issues` while blocking write tools like `update_issue` for sensitive agents.

The `create_comment` tool supports standard Linear Markdown. Your agents can write comments containing bold text, bullet points, strikethroughs, and user @mentions directly.

Your tokens are never stored on disk or exposed to the LLM. Vinkius handles the authorization layer in a zero-trust, ephemeral sandbox, passing your credentials directly to the API over TLS.

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