Linear MCP Server for OpenAI Agents SDK 12 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Linear through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="Linear Assistant",
instructions=(
"You help users interact with Linear. "
"You have access to 12 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Linear"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Linear MCP Server
Connect your Linear workspace to any AI agent and take full control of your issue tracking and sprint workflows through natural conversation.
The OpenAI Agents SDK auto-discovers all 12 tools from Linear through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Linear, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
What you can do
- User & Team Discovery — Retrieve the authenticated user profile and list all teams configured in your Linear workspace
- Issue Management — List, search, inspect and create issues with full metadata including assignees, labels, priority and state
- Project Oversight — Browse all active projects, view their status and drill into specific project details by ID
- Comments & Collaboration — Add comments to issues to keep your team context aligned without switching to the Linear app
- Cycle Tracking — List all sprint cycles for any team, including start/end dates and completion progress
- Label Organization — View all issue labels used for categorization across teams
The Linear MCP Server exposes 12 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Linear to OpenAI Agents SDK via MCP
Follow these steps to integrate the Linear MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 12 tools from Linear
Why Use OpenAI Agents SDK with the Linear MCP Server
OpenAI Agents SDK provides unique advantages when paired with Linear through the Model Context Protocol.
Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Linear + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Linear MCP Server delivers measurable value.
Automated workflows: build agents that query Linear, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries Linear, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Linear tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Linear to resolve tickets, look up records, and update statuses without human intervention
Linear MCP Tools for OpenAI Agents SDK (12)
These 12 tools become available when you connect Linear to OpenAI Agents SDK via MCP:
create_comment
The body supports Linear Markdown format including @mentions and ~~strikethrough~~. Add a comment to a Linear issue
create_issue
Requires the team ID and issue title. Optionally set description, assignee, priority (0=No priority, 1=Urgent, 2=High, 3=Normal, 4=Low) and label IDs. Create a new Linear issue
get_issue
Use the issue ID (UUID) or the human-readable identifier (e.g. TEAM-123). Get full details for a Linear issue
get_project
Get details for a specific Linear project
get_viewer
Useful to verify which account the API token belongs to. Get current authenticated Linear user details
list_cycles
Each cycle has a number, name, start date, end date and completion progress percentage. List Linear cycles (sprints) for a team
list_issues
Optionally filter by team ID to get issues for a specific team only. List Linear issues
list_labels
Optionally filter by team ID. Each label has a name, color and optional description. List Linear issue labels
list_projects
Projects group issues across multiple teams. Use optional limit to control how many results to fetch. List Linear projects
list_teams
Each team has a unique ID, name, key prefix and optional description. Use this to discover teams before querying their issues or cycles. List all Linear teams
search_issues
Optionally filter results to a specific team. Returns issues with identifier, title, state, priority, assignee and URL. Search Linear issues by text
update_issue
Provide the issue ID (UUID) and only the fields you want to change. Update an existing Linear issue
Example Prompts for Linear in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Linear immediately.
"Show me all unresolved issues assigned to the Engineering team."
"Create a new issue in the Backend team titled 'Add rate limiting to /api/search endpoint' with high priority."
"What's the current sprint cycle progress for the Mobile team?"
Troubleshooting Linear MCP Server with OpenAI Agents SDK
Common issues when connecting Linear to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Linear + OpenAI Agents SDK FAQ
Common questions about integrating Linear MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Linear with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Linear to OpenAI Agents SDK
Get your token, paste the configuration, and start using 12 tools in under 2 minutes. No API key management needed.