"Evaluating Mistral Small 27B for function calling and replacing Claude 3.7 in Roocode" matching MCP servers:

MCP server for Mistral AI providing OCR, TTS, and STT capabilities via Voxtral.

OCR images or pdfs, locally or by URLs by using Mistral OCR API (paid)

Provides OCR capabilities for images and PDFs using Mistral AI's OCR API, supporting both local files and URLs with output in markdown or JSON format.

Extracts text and images from PDFs and image files using the Mistral OCR API, with a security sandbox for file writes.

Enables OCR processing of local files and public URLs using Mistral OCR. Provides tools for health checks, key management, page listing, and generating Markdown output.

Enables AI assistants to interact with the full Mistral AI API, including chat completion, embeddings, fine-tuning, OCR, audio transcription, and more.

An MCP server that enables Claude to perform OCR on local files using Mistral AI's document processing capabilities. It converts documents and images into markdown format for seamless analysis and interaction.

Extracts text content from PDFs and images using Mistral's OCR API, enabling OCR capabilities in MCP-compatible clients like Cursor and Claude Desktop.

Enables OCR of scanned PDFs and images, returning searchable PDFs, Markdown, and JSON with block coordinates, with optional proofreading to correct OCR errors. Supports uploads via web console, public URL, or one-time token, and exposes tools for job status, page text, document listing, and deletion.

Enables Codex to delegate code reviews, coding tasks, image/video generation, and background investigations to Grok via MCP tools.

MCP server for Claude Code that enables image generation and editing via Azure AI Foundry's MAI Image API, writing files to disk and returning only the path.

Enables Claude to capture screenshots of the screen, windows, regions, and web pages, and compare screenshots for visual regression testing.

Gives LLM agents spatial awareness inside Autodesk Maya, enabling scene inspection and measurement, aesthetic and engineering audits, camera planning, checkpoint/rollback safety, asset import, and viewport or render previews. Agents can also execute arbitrary Python in Maya to build and verify 3D scenes against engineering rules instead of writing blind.

Enables AI-driven 3D modeling and scene creation in Blender, allowing LLMs to create, modify, and manipulate objects, materials, and assets through natural language.

A streamlined MCP server for XMP metadata embedding with beautiful formatting and smart filename indicators, enabling metadata embedding, reading, validation, and report generation for lifestyle, product, and orbit schemas.

An optimized Model Context Protocol server for document OCR processing using Mistral AI with support for high-performance batch operations and async connection pooling. It enables efficient extraction of text and tables from local files or URLs into structured markdown and HTML formats while minimizing token costs.

A single-file MCP server that enhances Claude Desktop with real-time web and X search, multi-tool agent, and image/video generation via xAI's Grok.

Enables Claude Code or Codex to act as an assistant editor inside Adobe Premiere Pro and DaVinci Resolve, logging footage, transcribing speech, assembling rough cuts and subtitles, and checking colour and loudness before delivery. It reads the saved project so later work follows manual edits, while quality gates refuse grades or files that fail checks.

An MCP server that enables Claude Code to generate context-aware images using local GPU-powered diffusion models, either automatically during coding or on-demand via slash commands.

Lets any LLM agent actually watch videos: a watch_video tool takes a URL or local file and returns scene-aware keyframes fused with a timestamped transcript, processed 100% locally with per-source caching.