Linear MCP | OAuth Linear connector for AI agents

CALL ANY TOOL

Read issues, manage projects and cycles, update status, and search across the workspace. Same toolkit, every framework, no auth plumbing.

linear_issues_list

List issues

Fetch issues with optional filters for assignee, state, team, label, and cycle.

Parameters

Name

Type

Required

Description

team_id

string

Optional

Filter by team ID

assignee_id

string

Optional

Filter by assignee user ID

state

string

Optional

Filter by state name (e.g. Todo, In Progress, Done)

label

string

Optional

Filter by label name

first

integer

Optional

Max issues to return

linear_issue_get

Get issue

linear_issue_create

Create issue

linear_issue_update

Update issue

linear_search_issues

Search issues

linear_projects_list

List projects

Build your Agent

Drop the toolkit in, point it at the user, and your agent can list Linear issues, create tickets, and update status from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["linear"], toolNames: ["linear_issues_list", "linear_search_issues", "linear_issue_create"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["linear"], toolNames: ["linear_issues_list", "linear_search_issues", "linear_issue_create"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["linear"], toolNames: ["linear_issues_list", "linear_search_issues", "linear_issue_create"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/linear",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start managing Linear workflows.

Search & recall

Copy the prompt

Copied

List all open issues assigned to me in [team].

Copy the prompt

Copied

What issues are In Progress in the current cycle?

Copy the prompt

Copied

Find all bugs labeled [critical] in [team].

Copy the prompt

Copied

What issues are in [project name]?

Action & creation

Copy the prompt

Copied

Create an issue in [team]: [title] — [description], priority High.

Copy the prompt

Copied

Move issue [ENG-123] to In Progress.

Copy the prompt

Copied

Assign [ENG-456] to [person name].

Copy the prompt

Copied

Add label [backend] to issue [ENG-789].

Cycles & projects

Copy the prompt

Copied

What is in the current cycle for [team]?

Copy the prompt

Copied

List all issues not yet started in the current cycle.

Copy the prompt

Copied

How many open issues are there by priority in [team]?

Copy the prompt

Copied

What projects are active in [team] right now?

SEE HOW AUTH WORKS

Users authorize Linear once. Their workspace credentials stay vaulted, every call is checked, and every action is logged.

1

Authorize

Your user connects

Linear

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Linear

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Linear

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Linear

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other engineering agents and MCP connectors. Working code, live demos, fork what fits.

ENGINEERING

DevOps assistant agent

Triage GitHub incidents, open Linear tickets, and notify the on-call channel in Slack with context already attached.

ENGINEERING

Engineering standup agent

Aggregate GitHub and GitLab activity, link to Jira, and post a daily standup digest to Slack. No async updates.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Issue changes lose team attribution

A shared Linear token looks fine in a demo. In production, every issue assignment, status update, and cycle change logs as the integration. Team attribution breaks. Per-engineer workload metrics break. Scalekit resolves the actual user's credential, so Linear tracks ownership and throughput correctly.

// shared bot token
token = "sk_linear_shared_xxx"
audit → bot_service_account
user_filter → broken

// scalekit · per-user
token = resolve(user_id)
audit → user_abc
scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Linear today. Jira, GitHub, GitLab tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Linear as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Linear oauth 2.0 stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Linear?

Yes. Pass a tool name filter to listScopedTools so the engineering agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Linear.

What happens when a user revokes Linear access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent work across multiple Linear workspaces?

One workspace per connected account. Per-user, per-workspace namespacing in the vault. A user can authorize multiple workspaces; cross-workspace access is denied by default.

Linear

Tools your engineering agent reaches for on Linear, scoped per user.