Comprehensive Blender MCP server with search+execute architecture — 220+ tools, asset management, real-time collaboration, visual programming, synthetic dataset generation, and more
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"blender-studio-pro-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Blender Studio MCP A comprehensive [Model Context Protocol](https://modelcontextprotocol.io/) server for Blender, giving AI assistants full control over a running Blender session. Built with a **search + execute** architecture that exposes 215 tools through just three MCP endpoints — keeping your AI's context window lean while retaining the full capability set. Compatible with Claude, Cursor, VS Code, and any MCP-capable client. --- ## Features - **220 Blender tools** across 50 categories — objects, materials, UV, shape keys, constraints, rigging, animation, NLA, rendering, physics, mesh cleanup, compositor, curves, drivers, library linking, custom properties, vertex attributes, world/environment, timeline markers, node groups, batch execution, asset management, real-time collaboration, visual programming, synthetic data generation, and more - **Search + execute architecture** — LLMs call `search_tools` to discover capabilities, then `execute_tool` or `execute_tools` to act, without loading all tool schemas into context - **Natural language search** — `search_tools("shiny metal")` finds `create_material`; examples and use-cases are embedded in every tool so AI agents discover the right tools faster - **Context-aware suggestions** — `blender://suggestions` resource returns the most relevant next tools based on scene state and command history - **Intelligent asset management** — index thousands of `.blend` files into a local SQLite + FTS5 database; full-text search, dependency tracking, Git-aware loading, and context-aware recommendations - **Real-time collaboration** — multi-client sessions with per-object locking, pub/sub event feed, heartbeat monitoring, and shared checkpoints; supports editor and observer roles - **Safe batch execution** — `execute_tools_safe` dry-runs all steps first, creates a checkpoint, and auto-rolls back if anything fails - **Sandbox mode** — set `BLENDER_MCP_SANDBOX=1` to block destructive operations (delete, clear, Python execution…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.