# How to integrate Gitlab MCP with LlamaIndex

```json
{
  "title": "How to integrate Gitlab MCP with LlamaIndex",
  "toolkit": "Gitlab",
  "toolkit_slug": "gitlab",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/gitlab/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/gitlab/framework/llama-index.md",
  "updated_at": "2026-05-12T10:13:08.718Z"
}
```

## Introduction

This guide walks you through connecting Gitlab to LlamaIndex 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 through natural language commands.
This guide will help you understand how to give your LlamaIndex 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.

## Also integrate Gitlab with

- [ChatGPT](https://composio.dev/toolkits/gitlab/framework/chatgpt)
- [Antigravity](https://composio.dev/toolkits/gitlab/framework/antigravity)
- [OpenAI Agents SDK](https://composio.dev/toolkits/gitlab/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/gitlab/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/gitlab/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/gitlab/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/gitlab/framework/codex)
- [Cursor](https://composio.dev/toolkits/gitlab/framework/cursor)
- [VS Code](https://composio.dev/toolkits/gitlab/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/gitlab/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/gitlab/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/gitlab/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/gitlab/framework/cli)
- [Google ADK](https://composio.dev/toolkits/gitlab/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/gitlab/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/gitlab/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/gitlab/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/gitlab/framework/crew-ai)

## TL;DR

Here's what you'll learn:
- Set your OpenAI and Composio API keys
- Install LlamaIndex and Composio packages
- Create a Composio Tool Router session for Gitlab
- Connect LlamaIndex to the Gitlab MCP server
- Build a Gitlab-powered agent using LlamaIndex
- Interact with Gitlab through natural language

## What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.
Key features include:
- ReAct Agent: Reasoning and acting pattern for tool-using agents
- MCP Tools: Native support for Model Context Protocol
- Context Management: Maintain conversation context across interactions
- Async Support: Built for async/await patterns

## 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

| Tool slug | Name | Description |
|---|---|---|
| `GITLAB_ARCHIVE_PROJECT` | Archive Project | Tool to archive a project. Use when you need to mark a project read-only after finishing active development. Call after confirming no further changes are required. |
| `GITLAB_CREATE_GROUP` | Create GitLab Group | Tool to create a new group in GitLab. Use when you need to establish a new group for projects or collaboration. |
| `GITLAB_CREATE_PROJECT` | Create Project | Tool to create a new project in GitLab. Implements POST /projects endpoint. |
| `GITLAB_CREATE_PROJECT_ISSUE` | Create Project Issue | Tool to create a new issue in a GitLab project. Use when you need to report a bug, request a feature, or track a task within a specific project. |
| `GITLAB_CREATE_REPOSITORY_BRANCH` | Create Repository Branch | Tool to create a new branch in a project. Use when you need to create a new branch from an existing branch or a specific commit in a GitLab project. |
| `GITLAB_DELETE_PROJECT` | Delete Project | Tool to delete a GitLab project by its ID. Use when you need to remove a project, either by marking it for later deletion or deleting it immediately. |
| `GITLAB_DOWNLOAD_PROJECT_AVATAR` | Download Project Avatar | Tool to download a project's avatar image. Use when you need the raw avatar bytes after confirming the project exists. |
| `GITLAB_ERASE_JOB` | Erase Job | Tool to erase the content of a specified job within a project. Use when you need to remove job artifacts and logs. |
| `GITLAB_GET_COMMIT_REFS` | Get Commit References | Tool to get all references (branches or tags) a commit is pushed to. Use when you need to find out which branches or tags a specific commit belongs to in a GitLab project. |
| `GITLAB_GET_COMMIT_SEQUENCE` | Get Commit Sequence | Tool to get the sequence number of a commit in a project by following parent links from the given commit. Use when you need to determine the order of a commit in the project's history. |
| `GITLAB_GET_GROUP` | Get Group Details | Tool to retrieve information about a specific group by its ID. Use when you need to get details of a GitLab group. |
| `GITLAB_GET_GROUP_MEMBER` | Get Group Member | Tool to retrieve details for a specific group member. Use when you need to fetch membership information for a user in a group after you know both group ID and user ID. |
| `GITLAB_GET_GROUPS` | Get Groups | Get Groups |
| `GITLAB_GET_JOB_DETAILS` | Get Job Details | Tool to retrieve details of a single job by its ID within a specified project. Use this when you need to fetch specific information about a particular CI/CD job. |
| `GITLAB_GET_MERGE_REQUEST_NOTES` | Get Merge Request Notes | Tool to fetch comments on a merge request. Use when you need to retrieve all notes for a specific merge request. |
| `GITLAB_GET_PROJECT` | Get Project | Tool to get a single project by ID or URL-encoded path. |
| `GITLAB_GET_PROJECT_LANGUAGES` | Get Project Languages | Tool to list programming languages used in a project with percentages. Use when you need the project language breakdown. |
| `GITLAB_GET_PROJECT_MEMBER` | Get Project Member | Tool to retrieve details for a specific project member. Use after confirming project and user IDs to fetch membership information for a project member. |
| `GITLAB_GET_PROJECT_MEMBER_ALL` | Get Project Member All | Tool to retrieve details for a specific project member (including inherited and invited members). Use when you need the effective membership info (including invitations and inheritance). |
| `GITLAB_GET_PROJECT_MERGE_REQUEST` | Get Project Merge Request | Tool to fetch full details for a single merge request when the MR IID is known. Use when you need to retrieve canonical metadata, description, state, branches, authors, and approval-related fields for a specific merge request. |
| `GITLAB_GET_PROJECT_MERGE_REQUEST_COMMITS` | Get Merge Request Commits | Tool to get commits of a merge request. Use when you need to retrieve all commits associated with a specific merge request. |
| `GITLAB_GET_PROJECT_MERGE_REQUESTS` | Get Project Merge Requests | Tool to retrieve a list of merge requests for a specific project. Use when you need to get all merge requests associated with a project, with options to filter by state, labels, milestones, and other attributes. |
| `GITLAB_GET_PROJECTS` | Get Projects | Tool to list all projects accessible to the authenticated user. Supports filtering. Private or group projects may be silently omitted if the token lacks sufficient scopes or group membership. |
| `GITLAB_GET_PROJECTS_ID_MERGE_REQUESTS_IID_DIFFS` | List Merge Request Diffs | Tool to list all diff versions of a merge request. Use when you need to inspect changes across different diff versions after creating or updating a merge request. |
| `GITLAB_GET_REPOSITORY_BRANCH` | Get Repository Branch | Tool to retrieve information about a specific branch in a project. Use when you need to get details for a single branch. |
| `GITLAB_GET_REPOSITORY_BRANCHES` | Get Repository Branches | Retrieves a list of repository branches for a project. Use this when you need to get all branches or search for specific branches within a GitLab project. |
| `GITLAB_GET_SINGLE_COMMIT` | Get Single Commit | Tool to get a specific commit identified by the commit hash or name of a branch or tag. Use this when you need to retrieve detailed information about a single commit in a GitLab project repository. |
| `GITLAB_GET_SINGLE_PIPELINE` | Get Single Pipeline | Tool to retrieve details of a single pipeline by its ID within a specified project. Use when you need to get information about a specific CI/CD pipeline. |
| `GITLAB_GET_USER` | Get User | Tool to retrieve information about a specific user by their ID. Use when you need to fetch details for a single GitLab user. |
| `GITLAB_GET_USER_PREFERENCES` | Get User Preferences | Tool to get the current user's preferences. Use when you need to retrieve the user's diff display and CI identity JWT settings after authentication. |
| `GITLAB_GET_USERS` | Get Users | Tool to retrieve a list of users from GitLab. Use this when you need to find user information, search for specific users, or filter users based on various criteria like activity status or creation date. |
| `GITLAB_GET_USERS_ID_STATUS` | Get User Status | Tool to get a user's status by ID. Use when you need to retrieve a GitLab user's current status message, emoji, and availability after identifying their user ID. |
| `GITLAB_GET_USER_STATUS` | Get User Status | Tool to get the current user's status. Use when displaying or verifying the authenticated user's GitLab status after login. |
| `GITLAB_GET_USER_SUPPORT_PIN` | Get User Support PIN | Tool to get details of the current user's Support PIN. Use when you need to retrieve the active support PIN and its expiration for the authenticated user. |
| `GITLAB_IMPORT_PROJECT_MEMBERS` | Import project members | Tool to import members from one project to another. Use when migrating members between projects. |
| `GITLAB_LIST_ALL_GROUP_MEMBERS` | List All Group Members | Tool to list all members of a group including direct, inherited, and invited members. Use when you need a comprehensive membership list beyond direct members. |
| `GITLAB_LIST_ALL_PROJECT_MEMBERS` | List All Project Members | Tool to list all members of a project (direct, inherited, invited). Use when you need the effective membership list including inherited and invited members. |
| `GITLAB_LIST_BILLABLE_GROUP_MEMBERS` | List Billable Group Members | Tool to list billable members of a top-level group (including its subgroups and projects). Use when generating billing reports; requires Owner role on the group. |
| `GITLAB_LIST_GROUP_MEMBERS` | List Group Members | Tool to list direct members of a group. Use when you need to retrieve or filter a group's direct membership. |
| `GITLAB_LIST_GROUP_PROJECTS` | List Group Projects | Tool to list projects within a GitLab group by group ID or full path. Use when discovering projects under a namespace or subgroup. |
| `GITLAB_LIST_PENDING_GROUP_MEMBERS` | List Pending Group Members | Tool to list pending members of a group and its subgroups and projects. Use when you need to review users awaiting approval or invited without an account. Call after confirming the top-level group ID. |
| `GITLAB_LIST_PIPELINE_JOBS` | List Pipeline Jobs | Tool to retrieve a list of jobs for a specified pipeline within a project. Use this when you need to inspect the status or details of jobs associated with a particular CI/CD pipeline. |
| `GITLAB_LIST_PROJECT_GROUPS` | List Project Groups | Tool to list ancestor groups of a project. Use when you need to retrieve all groups a project belongs to or is shared with. |
| `GITLAB_LIST_PROJECT_INVITED_GROUPS` | List Project Invited Groups | Tool to list groups invited to a project. Use when auditing which groups have access to a project. |
| `GITLAB_LIST_PROJECT_ISSUES` | List Project Issues | Tool to list issues for a project with filtering options (state, labels, search, assignee, author, etc.). Use when you need to browse, filter, or triage project issues to confirm IIDs or decide what to update/close. |
| `GITLAB_LIST_PROJECT_PIPELINES` | List Project Pipelines | Tool to retrieve a list of pipelines for a specified project. Use when you need to get information about CI/CD pipelines, such as their status, source, or creation/update times. |
| `GITLAB_LIST_PROJECT_SHAREABLE_GROUPS` | List Project Shareable Groups | Tool to list groups that can be shared with a project. Use before sharing a project to fetch eligible groups. |
| `GITLAB_LIST_PROJECT_TAGS` | List Project Repository Tags | Tool to retrieve a list of repository tags for a specified project. Use when you need to get all tags associated with a project in GitLab. |
| `GITLAB_LIST_PROJECT_TRANSFER_LOCATIONS` | List Project Transfer Locations | Tool to list namespaces available for project transfer. Use when you need to determine which groups a project can be transferred into. |
| `GITLAB_LIST_PROJECT_USERS` | List project users | Tool to list users of a project. Use after you have a project ID and want to retrieve its users. |
| `GITLAB_LIST_REPOSITORY_COMMITS` | List Repository Commits | Tool to get a list of repository commits in a project. Use when you need to retrieve commit history for a specific project, branch, or time range. |
| `GITLAB_LIST_USER_PROJECTS` | List User Projects | Tool to list projects owned by a specific user. Use after obtaining target user identity to fetch owned projects. |
| `GITLAB_POST_USER_SUPPORT_PIN` | Create Support PIN | Tool to create a support PIN for your authenticated user. Use when GitLab Support requests a PIN to verify your identity. |
| `GITLAB_PUT_USER_PREFERENCES` | Update User Preferences | Tool to update the current user's preferences. Use when adjusting default diff viewing and CI identity settings. |
| `GITLAB_SET_USER_STATUS` | Set User Status | Tool to set the current user's status. Use when you need to update availability or convey current mood on GitLab. |
| `GITLAB_SHARE_PROJECT_WITH_GROUP` | Share Project With Group | Tool to share a project with a group. Use when you need to grant a group specific access level to a project. |
| `GITLAB_START_PROJECT_HOUSEKEEPING` | Start Housekeeping Task | Tool to start the housekeeping task for a project. Use when you need to trigger manual maintenance or pruning on a repository. |
| `GITLAB_UPDATE_PROJECT_ISSUE` | Update Project Issue | Tool to update an existing issue in a GitLab project (title, description, labels, assignees, state, etc.). Use when you need to modify issue details, close/reopen issues, or manage labels and assignments. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Gitlab MCP server is an implementation of the Model Context Protocol that connects your AI agent to Gitlab. It provides structured and secure access so your agent can perform Gitlab operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

Before you begin, make sure you have:
- Python 3.8/Node 16 or higher installed
- A Composio account with the API key
- An OpenAI API key
- A Gitlab account and project
- Basic familiarity with async Python/Typescript

### 1. Getting API Keys for OpenAI, Composio, and Gitlab

No description provided.

### 2. Installing dependencies

No description provided.
```python
pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv
```

```typescript
npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv
```

### 3. Set environment variables

Create a .env file in your project root:
These credentials will be used to:
- Authenticate with OpenAI's GPT-5 model
- Connect to Composio's Tool Router
- Identify your Composio user session for Gitlab access
```bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id
```

### 4. Import modules

No description provided.
```python
import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();
```

### 5. Load environment variables and initialize Composio

No description provided.
```python
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")
```

```typescript
const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set");
if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set");
```

### 6. Create a Tool Router session and build the agent function

What's happening here:
- We create a Composio client using your API key and configure it with the LlamaIndex provider
- We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, gitlab)
- The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
- LlamaIndex will connect to this endpoint to dynamically discover and use the available Gitlab tools.
- The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.
```python
async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["gitlab"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Gitlab actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Gitlab actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)
```

```typescript
async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["gitlab"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
        description : "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Gitlab actions." ,
    llm,
    tools,
  });

  return agent;
}
```

### 7. Create an interactive chat loop

No description provided.
```python
async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")
```

```typescript
async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}
```

### 8. Define the main entry point

What's happening here:
- We're orchestrating the entire application flow
- The agent gets built with proper error handling
- Then we kick off the interactive chat loop so you can start talking to Gitlab
```python
async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err) {
    console.error("Failed to start agent:", err);
    process.exit(1);
  }
}

main();
```

### 9. Run the agent

When prompted, authenticate and authorise your agent with Gitlab, then start asking questions.
```bash
python llamaindex_agent.py
```

```typescript
npx ts-node llamaindex-agent.ts
```

## Complete Code

```python
import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["gitlab"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Gitlab actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Gitlab actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";
import { LlamaindexProvider } from "@composio/llamaindex";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) {
    throw new Error("OPENAI_API_KEY is not set in the environment");
  }
if (!COMPOSIO_API_KEY) {
    throw new Error("COMPOSIO_API_KEY is not set in the environment");
  }
if (!COMPOSIO_USER_ID) {
    throw new Error("COMPOSIO_USER_ID is not set in the environment");
  }

async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["gitlab"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
    description:
      "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Gitlab actions." ,
    llm,
    tools,
  });

  return agent;
}

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}

async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err: any) {
    console.error("Failed to start agent:", err?.message ?? err);
    process.exit(1);
  }
}

main();
```

## Conclusion

You've successfully connected Gitlab to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes Gitlab tools through an MCP endpoint
- LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
- The agent becomes more capable without increasing prompt size
- Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

## How to build Gitlab MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/gitlab/framework/chatgpt)
- [Antigravity](https://composio.dev/toolkits/gitlab/framework/antigravity)
- [OpenAI Agents SDK](https://composio.dev/toolkits/gitlab/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/gitlab/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/gitlab/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/gitlab/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/gitlab/framework/codex)
- [Cursor](https://composio.dev/toolkits/gitlab/framework/cursor)
- [VS Code](https://composio.dev/toolkits/gitlab/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/gitlab/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/gitlab/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/gitlab/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/gitlab/framework/cli)
- [Google ADK](https://composio.dev/toolkits/gitlab/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/gitlab/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/gitlab/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/gitlab/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/gitlab/framework/crew-ai)

## Related Toolkits

- [Supabase](https://composio.dev/toolkits/supabase) - Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure.
- [Codeinterpreter](https://composio.dev/toolkits/codeinterpreter) - Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms.
- [GitHub](https://composio.dev/toolkits/github) - GitHub is a code hosting platform for version control and collaborative software development. It streamlines project management, code review, and team workflows in one place.
- [Ably](https://composio.dev/toolkits/ably) - Ably is a real-time messaging platform for live chat and data sync in modern apps. It offers global scale and rock-solid reliability for seamless, instant experiences.
- [Abuselpdb](https://composio.dev/toolkits/abuselpdb) - Abuselpdb is a central database for reporting and checking IPs linked to malicious online activity. Use it to quickly identify and report suspicious or abusive IP addresses.
- [Alchemy](https://composio.dev/toolkits/alchemy) - Alchemy is a blockchain development platform offering APIs and tools for Ethereum apps. It simplifies building and scaling Web3 projects with robust infrastructure.
- [Algolia](https://composio.dev/toolkits/algolia) - Algolia is a hosted search API that powers lightning-fast, relevant search experiences for web and mobile apps. It helps developers deliver instant, typo-tolerant, and scalable search without complex infrastructure.
- [Anchor browser](https://composio.dev/toolkits/anchor_browser) - Anchor browser is a developer platform for AI-powered web automation. It transforms complex browser actions into easy API endpoints for streamlined web interaction.
- [Apiflash](https://composio.dev/toolkits/apiflash) - Apiflash is a website screenshot API for programmatically capturing web pages. It delivers high-quality screenshots on demand for automation, monitoring, or reporting.
- [Apiverve](https://composio.dev/toolkits/apiverve) - Apiverve delivers a suite of powerful APIs that simplify integration for developers. It's designed for reliability and scalability so you can build faster, smarter applications without the integration headache.
- [Appcircle](https://composio.dev/toolkits/appcircle) - Appcircle is an enterprise-grade mobile CI/CD platform for building, testing, and publishing mobile apps. It streamlines mobile DevOps so teams ship faster and with more confidence.
- [Appdrag](https://composio.dev/toolkits/appdrag) - Appdrag is a cloud platform for building websites, APIs, and databases with drag-and-drop tools and code editing. It accelerates development and iteration by combining hosting, database management, and low-code features in one place.
- [Appveyor](https://composio.dev/toolkits/appveyor) - AppVeyor is a cloud-based continuous integration service for building, testing, and deploying applications. It helps developers automate and streamline their software delivery pipelines.
- [Backendless](https://composio.dev/toolkits/backendless) - Backendless is a backend-as-a-service platform for mobile and web apps, offering database, file storage, user authentication, and APIs. It helps developers ship scalable applications faster without managing server infrastructure.
- [Baserow](https://composio.dev/toolkits/baserow) - Baserow is an open-source no-code database platform for building collaborative data apps. It makes it easy for teams to organize data and automate workflows without writing code.
- [Bench](https://composio.dev/toolkits/bench) - Bench is a benchmarking tool for automated performance measurement and analysis. It helps you quickly evaluate, compare, and track your systems or workflows.
- [Better stack](https://composio.dev/toolkits/better_stack) - Better Stack is a monitoring, logging, and incident management solution for apps and services. It helps teams ensure application reliability and performance with real-time insights.
- [Bitbucket](https://composio.dev/toolkits/bitbucket) - Bitbucket is a Git-based code hosting and collaboration platform for teams. It enables secure repository management and streamlined code reviews.
- [Blazemeter](https://composio.dev/toolkits/blazemeter) - Blazemeter is a continuous testing platform for web and mobile app performance. It empowers teams to automate and analyze large-scale tests with ease.
- [Blocknative](https://composio.dev/toolkits/blocknative) - Blocknative delivers real-time mempool monitoring and transaction management for public blockchains. Instantly track pending transactions and optimize blockchain interactions with live data.

## Frequently Asked Questions

### 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 LlamaIndex?

Yes, you can. LlamaIndex 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.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)