How to connect VLM Run to Grok Bot

Connect Grok Bot to VLM Run MCP. Extract invoice fields from uploaded pdfs, classify product images by defect type, and more using natural language, with authentication handled for you.

VLM Run logoVLM Run
Api Key

VLM Run is a multimodal AI platform for structured extraction, predictions, files, skills, feedback, and evaluations. It helps teams build reliable vision-language workflows without stitching together model, file, and eval infrastructure by hand.

11 Tools

Introduction

Grok is xAI's assistant, and its bot builder lets you create a personal agent that holds context, runs skills, and connects to the apps you already use through plugins.

This guide explains how to connect VLM Run to a Grok bot using Composio Connect, which handles OAuth, token refresh, and reliability so you do not have to. You add Composio as a plugin, authenticate once, then ask your bot to work with VLM Run in plain language.

Why use Composio?

Composio exposes 1,500+ apps to your Grok bot through a single connection, so you get:

  • Connect to 1,500+ apps with on-demand tool loading, so you do not fill your context window with unnecessary tool definitions.
  • Use programmatic tool calling through a remote workbench, letting the model write its own code to handle complex tool chaining. This reduces back-and-forth for frequent tool calls.
  • Handle large tool responses outside the model context to keep conversations lean.

Connecting VLM Run to Grok Bot

Once Grok Bot is set up, you connect VLM Run entirely from its interface, and the whole flow takes under a minute.

Set up Grok Bot

Get access. Grok Bot is included with Cursor Ultra, Cursor Premium Teams, and SuperGrok Heavy. Get the desktop app for macOS or Windows from x.ai/bot and sign in. An iPhone companion app is also available, and your bots sync across devices.

Create a bot. Pick a suggested role or define your own, then give it a short name, one primary job, and a short description of how it should work. Focused bots work best, because a clear role gives the bot more useful context over time.

Connect VLM Run

1. Add the Composio plugin

Click the button. The Composio listing on x.ai opens and launches Grok Bot for you. If the app does not open on its own, click Add to Grok Bot.

Add to Grok Bot

Composio for Grok Bot listing on x.ai with the Add to Grok Bot button

Grok Bot opens the Composio plugin, showing its connector and skills. Click Add.

Composio plugin sheet in Grok Bot with the Add button

2. Authenticate

Go to the Installed section and click the Composio entry. You'll see its connector and skills listed.

Installed Composio plugin showing the Authenticate button

Click Authenticate. You'll be taken to the Composio consent screen. Review the access it requests and click Authorize. Composio handles the OAuth handshake for you, so you never touch API keys or tokens.

Composio authorization screen with Authorize and Deny

3. Connect your VLM Run account

Back in the chat, ask your bot to connect to VLM Run or give it any VLM Run task.

For example, ask it to:

  • "Extract invoice fields from uploaded PDFs"
  • "Classify product images by defect type"
  • "Evaluate extraction quality against gold labels"

It will prompt you to authenticate and authorize access.

That's it. Composio's tools are now available in your Grok bot, and your VLM Run account is ready to use.

What is Grok Bot?

Grok is xAI's assistant, available as a chat interface and a bot builder for creating personal agents that run skills and connect to external apps.

With Composio Connect, your Grok bot can securely access apps like VLM Run through MCP without you sharing account credentials directly with the agent.

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

The VLM Run MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your VLM Run account. It provides structured and secure access to your multimodal agents, files, skills, extraction workflows, and runs, so your agent can upload files, extract structured data, execute agents, create reusable skills, and track results on your behalf.

  • Structured data extraction: Have your agent extract structured JSON from documents, images, videos, or audio using a supported domain, custom schema, or existing skill.
  • Multimodal agent execution: Direct your agent to choose an available VLM Run agent or provide an inline configuration, then run it against multimodal inputs.
  • File and skill management: Let the agent upload local files, find previously uploaded files, browse existing skills, or create a reusable skill from an uploaded zip, prompt, or chat session.
  • Run tracking and result retrieval: Instruct your agent to list extraction and agent runs, check work in progress, and retrieve completed results.
  • Schema and artifact discovery: Have your agent explore supported extraction domains and schemas, then list artifacts created during a chat session or agent execution.

Way Forward

Now that VLM Run is connected, extend your setup by connecting the other apps you already use every day, so your Grok bot can run true cross-app workflows end to end.

  • Connect Calendar to turn threads into scheduled meetings automatically.
  • Connect Slack or Teams to post summaries, approvals, and alerts where your team works.
  • Connect Notion, Linear, Jira, or Asana to convert requests into tickets, tasks, and docs.
  • Connect Drive, Dropbox, or OneDrive to fetch, file, and share attachments without manual steps.

Start with one workflow you do repeatedly, then keep adding apps as you find new handoffs. With everything behind a single connection, your bot can coordinate multiple tools safely and reliably in one conversation.

TOOLS

Supported Tools

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

Create Skill

Create a reusable skill from exactly one uploaded zip, prompt, or chat session.

Discover Extraction Schemas

List supported structured-extraction domains, or return the full JSON schema for one domain when domain is provided.

Execute Agent

Start a VLM Run agent execution from an existing agent name or inline configuration over multimodal inputs.

Extract Structured JSON

Start structured JSON extraction from images, a document, a video, or audio using a domain, custom schema, or skill.

Find Files

List uploaded files or find one by file ID or MD5 hash.

Find Skills

List VLM Run skills or find one exact skill by ID, name, and optional version.

Get Run

Get the current status and result of one structured-extraction prediction or agent execution; call repeatedly to poll asynchronous work.

List Agents

Return agents available to the connected account for selection before execution.

List Artifacts

List artifact metadata belonging to exactly one chat session or agent execution.

List Runs

List structured-extraction predictions or agent executions for the connected account.

Upload File

Upload a local file to VLM Run for extraction, agent input, or skill creation.

FAQ

Frequently asked questions

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

Yes, you can. Grok Bot 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 VLM Run tools.

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

Start with VLM Run.It takes 30 seconds.

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

Start building