Best Vision AI Skills & MCP Servers

MCP server that gives Claude Code the ability to watch and understand videos — extracts frames via ffmpeg and processes audio via multiple backends

MCP server exposing Mistral AI capabilities over MCP: chat, embeddings, FIM, vision, OCR, audio, agents, moderation, classification, files, batch, workflows, sampling, prompts, resources, and Streamable HTTP.

Prompt enhancer + asset pipeline for developers. One brief → a validated bundle (iOS AppIconSet, Android adaptive, PWA, favicon, OG, visionOS) via routed image models. Three modes: inline_svg (zero-key), external_prompt_only (paste into your subscription)

MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities

MCP server for EastRouter — vision tools that route through your EastRouter API key.

Authenticate and provision new tenants with initial document templates. Add and manage templates for existing tenants to standardize workflows. Connect to external services via HTTP as part of your setup or operations.

Async message queue for AI agents. Self-provision queues via MCP or REST — no human signup required. Push messages to other agents, poll your own queue, and coordinate across sessions. Free tier: 5 queues, 1000 messages/day, 24h TTL.

Provision new tenants with admin setup and initial document templates. Add document templates to existing tenants to expand your workspace. Authenticate and connect to external APIs to perform secure operations.

Perform quick, reliable arithmetic including addition, subtraction, multiplication, and division. Speed up everyday calculations and reduce errors across your workflows.