Skip to content

[MCP] VLM RunΒ #9214

@kishanprmr

Description

@kishanprmr

​ 🧩 Product Overview

VLM Run is a visual AI platform that extracts data from images, videos, audio, and documents. It helps automate analysis workflows, such as object detection, transcription, image/audio analysis, and document parsing.

With this Activepieces integration, VLM Run provides actions to analyze media/files.


​​ ⚠️ Important Note for Contributors

This feature must be submitted as a Piece following the Activepieces architecture. Submissions not following this format will not be accepted. Please make sure to review the Piece Development Guidelines before starting development.


​​ πŸ› οΈ Write Actions

Action Description
Analyze Audio Process an audio file, extracting features or transcription
Analyze Image Process an image (file or URL), extracting descriptions, detecting objects, etc.
Analyze Document Process a document (PDF, DOCX, etc.), extracting structured data or text.
Analyze Video Analyze a video file or URL, e.g. extract frames, detect content, etc.
Get File Gets file's metadata by ID.

​ πŸ“š API Reference


​ πŸ§ͺ Test Account Access


β€‹β€‹β€‹πŸ§‘β€πŸ’» New to Activepieces?

Activepieces is the leading open source AI automation platform. We have many apps (we call them Pieces), that are available within the builder and as MCPs. These apps are build with our TypeScript framework and are easy to build. Once they're merged to our repo, they will available as pieces in our automation builder and as MCPs to be used with AI agents and MCP clients.

We welcome contributions and in fact, we get excited over them. Start your journey here: https://www.activepieces.com/docs/developers/building-pieces/overview

Metadata

Metadata

Assignees

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions