Add Linear's hosted MCP server to Claude Code, sign in, and have it triage and update issues for you.
Out on Wednesday 28 October10 minutes, one build start to finish
Why this matters
Triage and ticket updates eat time every week. Linear's hosted MCP server lets Claude Code read and change issues with your own sign-in, so you can hand it the routine part while you check each change.
What you build
Claude reading, creating and updating Linear issues through Linear's MCP server.
Add Linear's hosted MCP server to Claude Code.
Sign in to Linear in the browser when Claude Code asks.
Ask it to find, create and update issues.
Have it triage a batch of new issues while you check each change.
The ideas behind it
A hosted MCP server
The tool vendor runs the server; you add its address to your client and sign in.
Acting as you
The agent works with your Linear permissions, so it sees and changes only what you could.
Human in the loop
You review each change during triage before trusting it with more.
Before you start
You need
Claude Code, and a Linear workspace you can sign in to.
Length
About 10 minutes, one build start to finish.
Questions
Does this need an API key?
No. You sign in to Linear in the browser when Claude Code asks.
Can it change many issues at once?
Yes, which is why the lab has you check each change during triage first.
Does the same approach work for other tools?
Yes. Many tools now offer hosted MCP servers that connect the same way.
Is the recorded lab free?
Yes. Watch it any time, follow the steps and keep the code you build.
How is it different from a Live Lab?
A recorded lab is one short build you follow on your own. A Live Lab builds a bigger part of the system in an hour, with time for your questions.
Then take it further
This build is one piece. The Live Lab Build a Team of AI Agents goes from here to a working part of a real system.
Split one agent into roles
A planner, an engineer and a reviewer, each with its own prompt and model.
Scope tools per role
Each agent calls only the tools its role needs, and every call is logged.
Decide when it pays
Compare the team with one agent on quality, latency and token cost.
The parts of a production agent system that lab builds, lit on the map:
Week 1Architect
Roles and modelsOne job per agent, a model chosen for that job, and a token budget.
OrchestrationA queue agents pick work from, with hand-offs a person can follow.
Context and memoryRetrieval with sources, memory across sessions, prompts laid out for the cache.
Tool callingTyped tools that act in GitHub, Linear and Google.
Week 2Build
MCP serversEvery tool behind an MCP gateway, scoped to the role that needs it.
Durable executionRuns that resume after a crash and never repeat a write.
Human in the loopA person approves anything that cannot be undone.
Week 3Secure and deploy
Identity and permissionsEach agent signs in as itself and acts on behalf of a user.
LLM gatewayRouting, caching and a budget on every model call.
Traces, evals and costEvery run traced, scored and charged to the agent that made it.
Multi-tenancyEach team or customer kept apart, in data and in the bill.
Week 4Govern and extend
Policy as codeRules checked on every action, not written in a document.
Signed skillsNew roles built from reviewed, signed skills.