product updateAnthropic

Anthropic releases 9 Claude connectors for Blender, Adobe, and creative software via MCP protocol

TL;DR

Anthropic has released nine connectors that integrate Claude with creative tools including Blender, Adobe Creative Cloud, Ableton, and Autodesk. The connectors use Anthropic's Model Context Protocol (MCP), allowing Claude to interface directly with creative software workflows.

2 min read
0

Anthropic releases 9 Claude connectors for Blender, Adobe, and creative software via MCP protocol

Anthropic has released nine connectors that integrate Claude with creative tools including Blender, Adobe Creative Cloud, Ableton, and Autodesk. The connectors use Anthropic's Model Context Protocol (MCP), allowing Claude to interface directly with creative software workflows.

The nine connectors

The full list of creative tool integrations:

  • Ableton: Grounds Claude's answers in official documentation for Live and Push
  • Adobe: Enables control of 50+ Creative Cloud tools including Photoshop, Premiere, and Express
  • Affinity by Canva: Automates batch image adjustments, layer renaming, and file exports
  • Autodesk Fusion: Creates and modifies 3D models through conversations for Fusion subscribers
  • Blender: Provides natural-language interface to Blender's Python API
  • Resolume Arena and Wire: Controls visual performance software in real time via natural language
  • SketchUp: Converts conversations into 3D model starting points
  • Splice: Searches catalog of royalty-free music samples from within Claude

Blender integration details

The Blender connector, built by Blender developers using MCP, allows 3D artists to analyze and debug entire scenes, build custom scripts to batch-apply changes to objects, and add new tools directly to Blender's interface using its Python API.

Anthropic has become a Blender Development Fund patron. The company notes that because Blender's connector uses MCP, other large language models can also connect to Blender.

What this means

This release represents Anthropic's first major push into vertical-specific integrations for creative professionals. The MCP protocol approach is strategic: by building connectors as open tools rather than proprietary integrations, Anthropic enables other AI models to use the same infrastructure while positioning Claude as the default choice for creative workflows. The Blender partnership is particularly notable—supporting an open-source project while gaining a connector that works with any LLM demonstrates a community-first approach that could accelerate MCP adoption across the creative tools ecosystem.

Related Articles

changelog

Anthropic Cuts False Positives in Fable 5's Biology Filter by 85%, Keeps Virology and Toxicology Blocked

Anthropic has cut false positives in Fable 5's biology safety classifier by roughly 85%, letting users ask about lab results, symptoms, and medical questions without being rerouted to the weaker Opus 5 model. Dual-use topics like virology, toxicology, and molecular design remain restricted, with Anthropic citing the difficulty of containing biological threats once released.

changelog

Anthropic SDK v0.121.0 Adds Session Budgets, Mid-Conversation Tool Changes, and GitHub Skills Auto-Loading

Anthropic released version 0.121.0 of its Python SDK on August 7, 2026, introducing a new beta for mid-conversation tool changes, session budgets, an advisor tool, pinned inference location, and skills auto-loading from GitHub. The update also removes retired Claude Opus 4.1 models from the API.

product update

Anthropic Adds Cross-Session Messaging to Claude Code v2.1.224

Claude Code v2.1.224 introduces cross-session messaging, letting separate Claude Code instances on macOS and Linux send each other summaries to coordinate work. The feature does not support approving permissions or executing commands remotely.

product update

Anthropic Sets Claude Code Auto Mode as Default Starting August 14

Anthropic will switch Claude Code's default permission setting to auto mode on August 14 for Pro, Max, and Team users. The company says its safety classifier caught 89% of dangerous commands in testing, compared to 13.6% for human reviewers, and will no longer charge extra tokens for the classifier itself.

Comments

Loading...