Linear
Create and manage Linear issues, comments, projects and labels through its GraphQL API.
About
Linear ships in the w6w first-party pack. It declares 11 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
- App id
io.w6w.linear- Version
- 0.2.4
- Author
- w6w
- Licence
- MIT
- Categories
- Project Management · Developer Tools
Overview
Linear creates and manages issues from a workflow through its GraphQL API — creating, updating, fetching and deleting issues, and adding comments to them, so a process outside Linear can file and track work the same way a person would in the app.
Projects can be created directly, and the reference data a workflow needs to build a well-formed issue — teams, labels, workflow states, users — can each be listed, which matters because Linear scopes most of that data per team rather than treating it as global.
A fit for turning an external event — a bug report, a support escalation, a triaged alert — into a tracked Linear issue, or keeping issue status in sync with progress happening in another system.
Build with Linear
Three routes to the same 11 actions. The Workflow tab is generated from Linear's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
List Issues
issue-get-many List issues, optionally filtered by team or assignee. Uses cursor pagination.
List Workflow States
state-get-many List workflow states. They are per-team — the same name has a different id on each team.
List Teams
team-get-many List the workspace's teams with their UUIDs — the id other actions need, not the ENG-style key.
List Users
user-get-many List the workspace's users — the source of the UUIDs used for `assigneeId`.
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying Linear's real ids.
{
"manifestVersion": "2",
"name": "linear-example",
"steps": [
{
"id": "comment-create",
"uses": {
"app": "io.w6w.linear",
"action": "comment-create",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"issueId": "<issueId>",
"body": "<body>"
}
}
]
}Here are some of the things you can do
-
Create Comment
performcomment-create -
Create Issue
performissue-create -
Get Issue
readissue-get -
List Issues
searchissue-get-many -
Update Issue
performissue-update
+6 more actions available
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for Linear, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to Linear. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "issue-create",
payload: {
teamId: "<value>",
title: "<value>",
// description: "<value>",
// assigneeId: "<value>",
// stateId: "<value>",
// priority: "<value>",
// labelIds: "<value>",
// projectId: "<value>",
// dueDate: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value);npm install -g @w6w/cliw6w run conn_YOUR_CONNECTION_ID --action issue-create --payload '{"teamId":"<value>","title":"<value>"}'Give an AI agent Linear — without giving it Linear's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.linear#comment-create",
"input": {
"issueId": "<issueId>",
"body": "<body>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's Linear connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
What the agent gets
Credentials it can't read
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
A tool surface scoped to the caller
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
A durable workflow in one call
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
Health-aware discovery
Linear's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. Linear itself is MIT, and the runtime that executes it is source-available (FSL).
Health checks
Linear declares its own checks, so its health is a property of the app rather than something the host guesses at.
Linear platform status
API rate-limit headroom
Request and query-complexity allowances remaining, read off the `X-RateLimit-*` and `X-Complexity-*` headers.