Use
COMPOSIOFOR YOU
Give Claude, Codex, or any harness secure access to 1700+ tools
CLI
One command to add tools and auth to your coding agent
Build
DEVELOPER PLATFORM
SDKs, tools, and auth for agents and backend apps
MCP GATEWAY
One managed MCP endpoint for all your tools and agents
ENTERPRISE
SSO, governance, and audit controls for deploying agents org-wide
Features
TRIGGERS
Start background agents from events across your connected apps
FIREWALLNEW
Blocks instructions hidden in tool results before your agent reads them
INSTANTNEW
Audio, video, search, browser and data tools, with no keys to manage
OPTIMIZATION
Lower cost per completed task with optimised tools and skills
FOR AGENTS
CLAUDE CODEX OPENCLAW CURSOR HERMES
BUILT FOR
OFFICE WORK SALES MARKETING PRODUCT & DESIGN CUSTOMER SUPPORT ENGINEERING HR & RECRUITING FINANCE & OPS E-COMMERCE CONTENT & MEDIA IT & SECURITY
ALL USE CASES
DOCS

How to integrate Linear MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Linear MCP. Create a new bug for team mobile, add a comment to issue lin-123, and more using natural language, with authentication handled for you.

Get started for free Get a demo

Linear

Oauth2Api Key

Linear is a modern issue tracking and project planning tool for fast-moving teams. It helps streamline workflows, organize projects, and boost productivity.

47 Tools12 Triggers

Managed auth

Connect Linear without auth hassles

We manage OAuth, API keys, token refresh, and scopes — you just build.

Book a call

Explore the MCP Gateway

Introduction

This guide walks you through connecting Linear to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Linear agent that can create and update issues, manage projects and milestones, post comments, track cycles, and search issues across teams through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Linear account through Composio's Linear MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:

How to set up and configure a Vercel AI SDK agent with Linear integration
Using Composio's Tool Router to dynamically load and access Linear tools
Creating an MCP client connection using HTTP transport
Building an interactive CLI chat interface with conversation history management
Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

streamText: Core function for streaming responses with real-time tool support
MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
OpenAI Provider: Native integration with OpenAI models

What is the Linear MCP server, and what's possible with it?

The Linear MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Linear account. It provides structured and secure access to your issues, projects, milestones, updates, comments, and teams, so your agent can search and update issues, manage projects, create milestones, publish project updates, and configure teams on your behalf.

Issue search and updates: Have your agent find issues by keywords, update their details, and remove labels that no longer apply.
Project planning: Let the agent create projects, adjust existing projects, and associate new projects with the right teams.
Milestone management: Direct your agent to create project milestones with clear names and optional target dates.
Project status updates: Instruct your agent to list, publish, and revise project updates so stakeholders stay informed.
Team and conversation management: Have your agent create or update teams, review workspace comments, and remove reactions from comments.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS

Prerequisites

Before you begin, make sure you have:

Node.js and npm installed
A Composio account with API key
An OpenAI API key

Getting API Keys for OpenAI and Composio

OpenAI API Key

Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
Keep the API key safe.

Composio API Key

Log in to the Composio dashboard.
Navigate to your API settings and generate a new API key.
Store this key securely as you'll need it for authentication.

Install required dependencies

bash

npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

@ai-sdk/openai: Vercel AI SDK's OpenAI provider
@ai-sdk/mcp: MCP client for Vercel AI SDK
@composio/core: Composio SDK for tool integration
ai: Core Vercel AI SDK
dotenv: Environment variable management

Set up environment variables

bash

OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

OPENAI_API_KEY: Your OpenAI API key for GPT model access
COMPOSIO_API_KEY: Your Composio API key for tool access
COMPOSIO_USER_ID: A unique identifier for the user session

Import required modules and validate environment

typescript

import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

What's happening:

We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
The dotenv/config import automatically loads environment variables
The MCP client import enables connection to Composio's tool server

Create Tool Router session and initialize MCP client

typescript

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["linear"],
  });

  const mcpUrl = session.mcp.url;

What's happening:

We're creating a Tool Router session that gives your agent access to Linear tools
The create method takes the user ID and specifies which toolkits should be available
The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
This session provides access to all Linear-related tools through the MCP protocol

Connect to MCP server and retrieve tools

typescript

const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();

What's happening:

We're creating an MCP client that connects to our Composio Tool Router session via HTTP
The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
The type: "http" is important - Composio requires HTTP transport
tools() retrieves all available Linear tools that the agent can use

Initialize conversation and CLI interface

typescript

let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to linear, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();

What's happening:

We initialize an empty messages array to maintain conversation history
A readline interface is created to accept user input from the command line
Instructions are displayed to guide the user on how to interact with the agent

Handle user input and stream responses with real-time tool feedback

typescript

rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

What's happening:

We use streamText instead of generateText to stream responses in real-time
toolChoice: "auto" allows the model to decide when to use Linear tools
stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
onStepFinish callback displays which tools are being used in real-time
We iterate through the text stream to create a typewriter effect as the agent responds
The complete response is added to conversation history to maintain context
Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Linear and Vercel AI SDK:

typescript

import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["linear"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to linear, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Linear agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

Real-time streaming responses for a better user experience with typewriter effect
Live tool execution feedback showing which tools are being used as the agent works
Dynamic tool loading through Composio's Tool Router with secure authentication
Multi-step tool execution with configurable step limits (up to 10 steps)
Comprehensive error handling for robust agent execution
Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

TOOLS & TRIGGERS

Supported Tools and Triggers

Every Linear action and event your agent gets out of the box.

Archive issue

Archives an existing Linear issue by its UUID or shorthand identifier, removing it from active views while preserving its data for future reference.

Archive Project

Archives an existing Linear project by its UUID, removing it from active views.

Archive Project Update

Archives a project update in Linear, hiding it from the default view while preserving its data.

Create attachment

Creates a new attachment and associates it with a specific, existing Linear issue.

Add reaction to comment

Tool to add a reaction to an existing Linear comment.

Create a comment

Creates a new comment on a specified Linear issue.

Create linear issue

Creates an issue in a specified Linear team with a title and optional project, description, assignee, state, priority, cycle, due date, and other properties.

Create issue relation

Create a relationship between two Linear issues using the issueRelationCreate mutation.

Create a label

Creates a label for a specified Linear team, or returns an existing exact-name match found in the team's initial label results.

Create Project

Creates a new Linear project with specified name and team associations.

Create Project Milestone

Tool to create a project milestone in Linear with a name and optional target date and sort order.

Create Project Update

Tool to create a project status update post for a Linear project.

Create Team

Creates a new team in Linear with the specified name and key.

Delete issue

Archives an existing Linear issue by its ID, which is Linear's standard way of deleting issues; the operation is idempotent.

Download issue files

Downloads a Linear Attachment record or a private upload embedded in issue/comment Markdown; `file_name` must include the correct extension.

Get a comment

Retrieves a single Linear comment by its unique ID.

Get current user

Gets the currently authenticated Linear user's ID, name, email, and other profile information.

Get cycles by team ID

Lists cycles for a specified Linear team ID, including progress, creation and end times, and history.

Get create issue default params

Fetches a Linear team's default issue estimate and state, useful for pre-filling new issue forms.

Get Linear issue

Retrieves a Linear issue by UUID or shorthand identifier, including its details, parent, cycle, attachments, comments and subscribers.

Get Linear project

Retrieves a single Linear project by its unique identifier.

Get Project Update

Retrieves a specific project update by its unique identifier.

List comments

Lists comments from Linear workspace accessible to the authenticated user.

List issue drafts

Lists the connected user's issue drafts for review or editing.

List issues by team ID

Tool to list all issues for a specific Linear team, scoped by team ID.

Get all cycles

Lists cycles across the Linear account without filters, including team IDs and scheduled end times.

List Linear issues

Lists non-archived Linear issues with optional project and assignee filters, returning a paginated issues array and page_info.

Get labels

Retrieves paginated Linear issue labels for a specified team or across the workspace.

List linear projects

Retrieves all projects from the Linear account.

List Linear states

Retrieves all workflow states for a specified team in Linear, representing the stages an issue progresses through in that team's workflow.

Get teams

Lists visible Linear teams with their members and project IDs, with pagination for teams but not nested members or projects.

List Linear users

Lists workspace users with IDs, names, emails, and active status.

List project updates

Retrieves all project updates from the Linear workspace.

Remove label from Linear issue

Removes a specified label from a Linear issue using the issue and label IDs, and returns the updated issue and labels.

Remove reaction from comment

Tool to remove a reaction on a comment.

Resolve comment

Marks a Linear comment as resolved.

Run Query or Mutation

Execute a Linear GraphQL query or mutation to retrieve or change accessible data.

Search Linear issues

Searches Linear issues by full-text query, with pagination and an option to include archived issues.

Unarchive Project Update

Unarchive a previously archived project update in Linear.

Unresolve a comment

Unresolves a previously resolved Linear comment, marking it as requiring attention again.

Update issue

Updates an existing Linear issue by ID, requiring at least one field to modify; supplied fields overwrite existing values and labels replace the label set.

Update a comment

Tool to update an existing Linear comment's body text.

Update Project

Tool to update an existing Linear project.

Update Project Update

Tool to update an existing Linear project update post.

Update Team

Updates an existing Linear team's settings, including its name, key, cycle settings, and workflow state configuration.

Validate credential

Validates the Linear API credentials by checking if the authentication token can successfully query the current user.

Who Am I

Return the identity (name, email) of the connected Linear account.

FRAMEWORKS

How to build Linear MCP Agent with another framework

Claude Code

Use Linear MCP with Claude Code

Cursor

Use Linear MCP with Cursor

ChatGPT

Use Linear MCP with ChatGPT

Claude Cowork

Use Linear MCP with Claude Cowork

Antigravity

Use Linear MCP with Antigravity

OpenAI Agents SDK

Use Linear MCP with OpenAI Agents SDK

Claude Agent SDK

Use Linear MCP with Claude Agent SDK

Grok Bot

Use Linear MCP with Grok Bot

Muse

Use Linear MCP with Muse

Codex

Use Linear MCP with Codex

Kimi Code

Use Linear MCP with Kimi Code

Grok Build

Use Linear MCP with Grok Build

VS Code

Use Linear MCP with VS Code

OpenCode

Use Linear MCP with OpenCode

OpenClaw

Use Linear MCP with OpenClaw

Hermes

Use Linear MCP with Hermes

Atomic Agent

Use Linear MCP with Atomic Agent

CLI

Use Linear MCP with CLI

Google ADK

Use Linear MCP with Google ADK

LangChain

Use Linear MCP with LangChain

Mastra AI

Use Linear MCP with Mastra AI

LlamaIndex

Use Linear MCP with LlamaIndex

CrewAI

Use Linear MCP with CrewAI

Pydantic AI

Use Linear MCP with Pydantic AI

AutoGen

Use Linear MCP with AutoGen

MORE TOOLKITS

Explore Other Toolkits

Toolkit marketplace

Google Sheets

Oauth2

Google Sheets is a cloud-based spreadsheet tool for real-time collaboration and data analysis. It lets teams work together from anywhere, updating information instantly.

Notion

Oauth2Api Key

Notion is a collaborative workspace for notes, docs, wikis, and tasks. It streamlines team knowledge, project tracking, and workflow customization in one place.

Airtable

Oauth2Api Key

Airtable combines the flexibility of spreadsheets with the power of a database for easy project and data management. Teams use Airtable to organize, track, and collaborate with custom views and automations.

Asana

Oauth2

Asana is a collaborative work management platform for teams to organize and track projects. It streamlines teamwork, boosts productivity, and keeps everyone aligned on goals.

FAQ

Frequently asked questions

With a standalone Linear MCP server, the agents and LLMs can only access a fixed set of Linear tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Linear and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Vercel AI SDK v6 fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Linear tools.

Yes, absolutely. You can configure which Linear scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Linear data and credentials are handled as safely as possible.

Start with Linear.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Linear tool your agent needs.Free to start.

Start building

How to integrate Linear MCP with Vercel AI SDK v6

Connect Linear without auth hassles

Introduction

Also integrate Linear with

TL;DR

What is Vercel AI SDK?

What is the Linear MCP server, and what's possible with it?

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

How the Composio SDK works

Step-by-step Guide

Prerequisites

Getting API Keys for OpenAI and Composio

Install required dependencies

Set up environment variables

Import required modules and validate environment

Create Tool Router session and initialize MCP client

Connect to MCP server and retrieve tools

Initialize conversation and CLI interface

Handle user input and stream responses with real-time tool feedback

Complete Code

Conclusion

Supported Tools and Triggers

How to build Linear MCP Agent with another framework

Claude Code

Cursor

ChatGPT

Claude Cowork

Antigravity

OpenAI Agents SDK

Claude Agent SDK

Grok Bot

Muse

Codex

Kimi Code

Grok Build

VS Code

OpenCode

OpenClaw

Hermes

Atomic Agent

CLI

Google ADK

LangChain

Mastra AI

LlamaIndex

CrewAI

Pydantic AI

AutoGen

Explore Other Toolkits

Google Sheets

Notion

Airtable

Asana

Frequently asked questions

What are the differences in Tool Router MCP and Linear MCP?

Can I use Tool Router MCP with Vercel AI SDK v6?

Can I manage the permissions and scopes for Linear while using Tool Router?

How safe is my data with Composio Tool Router?

Start with Linear.It takes 30 seconds.