How to integrate Penpot MCP with LlamaIndex

This guide walks you through connecting Penpot to LlamaIndex using the Composio tool router. By the end, you'll have a working Penpot agent that can review comments on penpot design files, create prototype links for mobile screens, list recent changes in team projects through natural language commands. This guide will help you understand how to give your LlamaIndex agent real control over a Penpot account through Composio's Penpot MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Penpot logoPenpot
Api Key

Penpot is an open-source design and prototyping platform for product teams. It helps teams collaborate on UI design with web-based, developer-friendly workflows.

90 Tools

Introduction

This guide walks you through connecting Penpot to LlamaIndex using the Composio tool router. By the end, you'll have a working Penpot agent that can review comments on penpot design files, create prototype links for mobile screens, list recent changes in team projects through natural language commands.

This guide will help you understand how to give your LlamaIndex agent real control over a Penpot account through Composio's Penpot MCP server.

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

Also integrate Penpot with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AICrewAI

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 Penpot
  • Connect LlamaIndex to the Penpot MCP server
  • Build a Penpot-powered agent using LlamaIndex
  • Interact with Penpot 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 Penpot MCP server, and what's possible with it?

The Penpot MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Penpot account. It provides structured and secure access to your teams, projects, design files, comments, and webhooks, so your agent can organize projects, manage files, coordinate feedback, find design work, and review team membership on your behalf.

  • Team and project organization: Have your agent create teams and projects, list your existing workspaces, and retrieve project or team details.
  • Design file management: Let the agent create and update design files, inspect file information, and list every file within a project.
  • Design search and discovery: Direct your agent to search for Penpot files by name or content across a team.
  • Collaborative design feedback: Instruct your agent to create comment threads at specific places in a design and retrieve existing discussions for review.
  • Team updates and notifications: Have your agent list team members and create webhooks that notify your systems about team events.

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:

  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

Step by step10 STEPS
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 Penpot account and project
  • Basic familiarity with async Python/Typescript
2

Getting API Keys for OpenAI, Composio, and Penpot

OpenAI API key (OPENAI_API_KEY)
  • Go to the OpenAI dashboard
  • Create an API key if you don't have one
  • Assign it to OPENAI_API_KEY in .env
Composio API key and user ID
  • Log into the Composio dashboard
  • Copy your API key from Settings
    • Use this as COMPOSIO_API_KEY
  • Pick a stable user identifier (email or ID)
    • Use this as COMPOSIO_USER_ID
3

Installing dependencies

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

Create a new Typescript project and install the necessary dependencies:

  • @composio/llamaindex: Composio's LlamaIndex integration
  • @llamaindex/openai: OpenAI LLM integration
  • @llamaindex/tools: MCP client for LlamaIndex
  • @llamaindex/workflow: Workflow framework for LlamaIndex
  • dotenv: Environment variable management
4

Set environment variables

bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id

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 Penpot access
5

Import modules

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();

Create a new file called penpot_llamaindex_agent.ts and import the required modules:

Key imports:

  • dotenv.config loads .env at runtime
  • readline gives us a simple CLI chat loop
  • Composio is the main Composio SDK client
  • mcp connects to an MCP endpoint
  • createAgent builds a LlamaIndex agent
  • openai configures the LLM backend
6

Load environment variables and initialize Composio

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");

What's happening:

This ensures missing credentials cause early, clear errors before the agent attempts to initialise.

7

Create a Tool Router session and build the agent function

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: ["penpot"],
    },
  );

  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 Penpot actions." ,
    llm,
    tools,
  });

  return agent;
}

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, penpot)
  • 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 Penpot tools.
  • The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.
8

Create an interactive chat loop

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();
}

What's happening:

  • We're creating a direct terminal interface to chat with Penpot
  • The LLM's responses are streamed to the CLI for faster interaction.
  • The agent uses context to maintain conversation history
  • The agent processes the request, selects appropriate Penpot tools, and returns a result
  • We extract the answer from the result data structure and display it to the user
  • You can type 'quit' or 'exit' to stop the chat loop gracefully
  • Agent responses and any errors are streamed in a clear, readable format
9

Define the main entry point

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

main();

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 Penpot
10

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with Penpot, then start asking questions.

Complete Code

Here's the complete code to get you started with Penpot and LlamaIndex:

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: ["penpot"],
    },
  );

  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 Penpot 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 Penpot to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Penpot 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.
TOOLS

Supported Tools

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

Create Access Token

Tool to create a personal access token for API authentication in Penpot.

Create Comment Thread

Tool to create a new comment thread on a Penpot file at a specific position.

Create File

Tool to create a new design file in a Penpot project.

Create Project

Tool to create a new project within a team in Penpot.

Create Team

Tool to create a new team in Penpot.

Create Team Access Request

Tool to request an invitation to join a Penpot team.

Create Webhook

Create a webhook for a team to receive event notifications.

Delete Access Token

Tool to delete a personal access token from Penpot.

Delete Comment

Tool to delete a comment from a Penpot design file.

Delete File Snapshot

Tool to delete a file snapshot in Penpot.

Delete Project

Tool to delete a project from Penpot.

Delete Team

Tool to delete a team from Penpot.

Permanently Delete Team Files

Tool to permanently delete specified files from a Penpot team.

Delete Team Invitation

Tool to delete a pending team invitation in Penpot.

Delete Team Member

Tool to remove a member from a team in Penpot.

Delete Webhook

Tool to delete a webhook by its UUID.

Duplicate File

Tool to duplicate a single file within the same team in Penpot.

Duplicate Project

Tool to duplicate an entire Penpot project with all its files.

Get Access Tokens

Tool to list all personal access tokens for the authenticated user.

Get All Projects

Tool to retrieve all projects across all teams in Penpot.

Get Builtin Templates

Tool to get the list of builtin templates available in Penpot.

Get Comments

Tool to retrieve all comments in a comment thread.

Get Comment Thread

Tool to retrieve a specific comment thread from a Penpot file.

Get Comment Threads

Tool to retrieve all comment threads for a Penpot file.

Get File

Tool to retrieve a Penpot file by its ID.

Get File Info

Tool to retrieve basic information about a Penpot file by its ID.

Get File Libraries

Tool to retrieve libraries linked to a Penpot file.

Get File Object Thumbnails

Tool to retrieve thumbnails for objects in a Penpot file.

Get File Snapshots

Retrieves all snapshots for a specific Penpot file.

Get File Summary

Tool to retrieve a summary of file contents and statistics from Penpot.

Get Font Variants

Tool to retrieve font variants for a team, file, project, or share in Penpot.

Get Library File References

Tool to get files that reference a shared library.

Get Library Usage

Tool to get usage statistics for a library.

Get Owned Teams

Tool to list teams owned by the current user.

Get Page

Tool to retrieve page data from a Penpot file.

Get Profiles for File Comments

Tool to retrieve profiles of users who have commented on a Penpot file.

Get Project

Tool to retrieve detailed information about a specific Penpot project by its ID.

Get Project Files

Tool to retrieve all files in a Penpot project.

Get SSO Provider

Tool to retrieve SSO provider information for an email address.

Get Subscription Usage

Tool to get subscription usage information for the current user.

Get Team

Tool to retrieve team details by ID.

Get Team Deleted Files

Tool to retrieve deleted files from a team's trash in Penpot.

Get Team Info

Tool to retrieve detailed information about a specific Penpot team by its ID.

Get Team Invitations

Tool to list pending invitations for a team in Penpot.

Get Team Members

Tool to list all members of a team in Penpot.

Get Teams

Tool to list all teams the authenticated user is a member of.

Get Team Shared Files

Tool to retrieve shared library files for a Penpot team.

Get Team Stats

Tool to retrieve statistics for a specific Penpot team by its ID.

Get Team Users

Tool to retrieve users in a team by team ID or file ID.

Get Unread Comment Threads

Tool to retrieve comment threads with unread comments for a specific team.

Get View Only Bundle

Tool to retrieve data bundle for view-only file access in Penpot.

Get Webhooks

Tool to retrieve all webhooks configured for a team.

Has File Libraries

Tool to check if a Penpot file has linked libraries.

Ignore File Library Sync Status

Tool to ignore library sync status updates for a file.

Link File to Library

Tool to link a file to a library in Penpot.

Lock File Snapshot

Tool to lock a file snapshot in Penpot to prevent deletion.

Logout

Tool to clear the authentication cookie and logout the current session.

Mark All Threads As Read

Tool to mark all comment threads as read in Penpot.

Move Files

Tool to move files from one project to another in Penpot.

Move Project

Tool to move a project to a different team in Penpot.

Prepare Register Profile

Tool to prepare user registration by validating email and sending verification in Penpot.

Push Audit Events

Tool to push audit events to Penpot for tracking system behavior and user actions.

Register Profile

Tool to complete user registration with profile details using a verification token.

Rename File

Tool to rename a design file in Penpot.

Rename Project

Tool to rename an existing project in Penpot.

Request Profile Recovery

Tool to request a password/profile recovery email.

Restore Deleted Team Files

Tool to restore deleted files in a Penpot team.

Restore File Snapshot

Tool to restore a Penpot file to a previous snapshot.

Search Files

Tool to search for files by name or content in a Penpot team.

Send User Feedback

Tool to send user feedback to Penpot.

Set File Shared

Tool to set file sharing status in Penpot (enable/disable shared library).

Unlink File from Library

Tool to unlink a file from a shared library in Penpot.

Unlock File Snapshot

Tool to unlock a locked file snapshot in Penpot.

Update Comment

Tool to update the content of an existing comment in a Penpot design file.

Update Comment Thread

Tool to update the resolution status of a comment thread in Penpot.

Update Comment Thread Frame

Tool to update the frame associated with a comment thread in Penpot.

Update Comment Thread Position

Tool to update the position of a comment thread in Penpot.

Update Comment Thread Status

Tool to update the status of a comment thread in Penpot (e.

Update File

Tool to update a Penpot file with changes.

Update File Library Sync Status

Tool to update the synchronization status of a file->library link.

Update File Snapshot

Tool to update a file snapshot metadata in Penpot.

Update Font

Tool to update a font's metadata in Penpot.

Update Profile

Tool to update the current authenticated user's profile information.

Update Profile Notifications

Tool to update notification settings for the authenticated user's profile.

Update Profile Props

Tool to update custom properties for the authenticated user's profile.

Update Project Pin

Tool to update the pin status of a project in Penpot.

Update Team

Tool to update team settings in Penpot.

Update Team Invitation Role

Tool to update the role of a pending team invitation in Penpot.

Update Webhook

Tool to update an existing webhook configuration.

Verify Token

Tool to verify an authentication or registration token in Penpot.

FRAMEWORKS

How to build Penpot MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Penpot MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Penpot MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Penpot MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Penpot MCP with Claude Cowork

Codex logo

Codex

Use Penpot MCP with Codex

OpenClaw logo

OpenClaw

Use Penpot MCP with OpenClaw

Hermes logo

Hermes

Use Penpot MCP with Hermes

CLI logo

CLI

Use Penpot MCP with CLI

Google ADK logo

Google ADK

Use Penpot MCP with Google ADK

LangChain logo

LangChain

Use Penpot MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Penpot MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Penpot MCP with Mastra AI

CrewAI logo

CrewAI

Use Penpot MCP with CrewAI

FAQ

Frequently asked questions

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

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 Penpot tools.

Yes, absolutely. You can configure which Penpot 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 Penpot data and credentials are handled as safely as possible.

Start with Penpot.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies