How to integrate Gitlab MCP with Vercel AI SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Gitlab Logo
Vercel AI SDK Logo
divider

Introduction

This guide walks you through connecting Gitlab to Vercel AI SDK using the Composio tool router. By the end, you'll have a working Gitlab agent that can create new gitlab group for qa team, open bug issue in frontend project, create branch from latest main commit, archive completed api migration project through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Gitlab account through Composio's Gitlab 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 Gitlab integration
  • Using Composio's Tool Router to dynamically load and access Gitlab 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
  • Step Counting: Control multi-step tool execution
  • OpenAI Provider: Native integration with OpenAI models

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

The Gitlab MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Gitlab account. It provides structured and secure access to your repositories, projects, and issues, so your agent can perform actions like creating projects, managing issues, handling branches, and automating DevOps workflows on your behalf.

  • Project and group automation: Instantly create new Gitlab projects or organize your workspaces by setting up project groups—all without manual clicks.
  • Issue creation and tracking: Have your agent report bugs, request features, or open new issues in specific projects to keep your team on top of tasks.
  • Branch management: Let your agent create repository branches from any commit or base branch, making it easy to streamline your development process.
  • Project lifecycle management: Archive completed projects or delete unneeded ones, keeping your workspace clean and up to date with minimal effort.
  • Commit and job insights: Retrieve commit references, determine commit sequence in project history, or erase job artifacts and logs for deeper CI/CD control.

Supported Tools & Triggers

Tools
Archive ProjectTool to archive a project.
Create GitLab GroupTool to create a new group in gitlab.
Create ProjectTool to create a new project in gitlab.
Create Project IssueTool to create a new issue in a gitlab project.
Create Repository BranchTool to create a new branch in a project.
Delete ProjectTool to delete a gitlab project by its id.
Download Project AvatarTool to download a project’s avatar image.
Erase JobTool to erase the content of a specified job within a project.
Get Commit ReferencesTool to get all references (branches or tags) a commit is pushed to.
Get Commit SequenceTool to get the sequence number of a commit in a project by following parent links from the given commit.
Get Group DetailsTool to retrieve information about a specific group by its id.
Get Group MemberTool to retrieve details for a specific group member.
Get GroupsGet groups
Get Job DetailsTool to retrieve details of a single job by its id within a specified project.
Get Merge Request NotesTool to fetch comments on a merge request.
Get ProjectTool to get a single project by id or url-encoded path.
Get Project LanguagesTool to list programming languages used in a project with percentages.
Get Project MemberTool to retrieve details for a specific project member.
Get Project Member AllTool to retrieve details for a specific project member (including inherited and invited members).
Get Merge Request CommitsTool to get commits of a merge request.
Get Project Merge RequestsTool to retrieve a list of merge requests for a specific project.
Get ProjectsTool to list all projects accessible to the authenticated user.
List Merge Request DiffsTool to list all diff versions of a merge request.
Get Repository BranchTool to retrieve information about a specific branch in a project.
Get Repository BranchesRetrieves a list of repository branches for a project.
Get Single CommitTool to get a specific commit identified by the commit hash or name of a branch or tag.
Get Single PipelineTool to retrieve details of a single pipeline by its id within a specified project.
Get UserTool to retrieve information about a specific user by their id.
Get User PreferencesTool to get the current user's preferences.
Get UsersTool to retrieve a list of users from gitlab.
Get User StatusTool to get a user's status by id.
Get User StatusTool to get the current user's status.
Get User Support PINTool to get details of the current user's support pin.
Import project membersTool to import members from one project to another.
List All Group MembersTool to list all members of a group including direct, inherited, and invited members.
List All Project MembersTool to list all members of a project (direct, inherited, invited).
List Billable Group MembersTool to list billable members of a top-level group (including its subgroups and projects).
List Group MembersTool to list direct members of a group.
List Pending Group MembersTool to list pending members of a group and its subgroups and projects.
List Pipeline JobsTool to retrieve a list of jobs for a specified pipeline within a project.
List Project GroupsTool to list ancestor groups of a project.
List Project Invited GroupsTool to list groups invited to a project.
List Project PipelinesTool to retrieve a list of pipelines for a specified project.
List Project Shareable GroupsTool to list groups that can be shared with a project.
List Project Repository TagsTool to retrieve a list of repository tags for a specified project.
List Project Transfer LocationsTool to list namespaces available for project transfer.
List project usersTool to list users of a project.
List Repository CommitsTool to get a list of repository commits in a project.
List User ProjectsTool to list projects owned by a specific user.
Create Support PINTool to create a support pin for your authenticated user.
Update User PreferencesTool to update the current user's preferences.
Set User StatusTool to set the current user's status.
Share Project With GroupTool to share a project with a group.
Start Housekeeping TaskTool to start the housekeeping task for a project.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router follows a three-phase workflow:

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

Step-by-step Guide

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 { experimental_createMCPClient as 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: ["gitlab"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Gitlab 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 Gitlab-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 Gitlab 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 gitlab, 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 Gitlab 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 Gitlab 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 { experimental_createMCPClient as 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: ["gitlab"],
  });

  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 gitlab, 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 Gitlab 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.

How to build Gitlab MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Gitlab MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Gitlab MCP with Claude Agent SDK

Google ADK

Google ADK

Use Gitlab MCP with Google ADK

LangChain

LangChain

Use Gitlab MCP with LangChain

Mastra AI

Mastra AI

Use Gitlab MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Gitlab MCP with LlamaIndex

CrewAI

CrewAI

Use Gitlab MCP with CrewAI

FAQ

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

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

Can I use Tool Router MCP with Vercel AI SDK?

Yes, you can. Vercel AI SDK 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 Gitlab tools.

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

Yes, absolutely. You can configure which Gitlab 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.

How safe is my data with Composio Tool Router?

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 Gitlab data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free