DCC-MCP-CoreGateway-first MCP + Skills for DCC AI

Production-grade foundation combining MCP, zero-code Skills, dynamic capability routing, and release-ready CLI/server binaries for Maya, Blender, Houdini, Photoshop, and custom studio hosts.

Get Started

Why MCP + Skills?

Install dcc-mcp Skill

GitHub

🤖

Agent-Ready Entry

Install the public dcc-mcp Skill, then use dcc-mcp-cli to inventory, search, inspect, and call typed DCC capabilities.

🎯

Dynamic Capability Routing

Agents search, describe, load skills, and call tools through one gateway instead of carrying every backend tool in context.

🔌

Zero-Code Skill Registration

Write SKILL.md + scripts/ → instant MCP tools. No Python glue code needed. Supports Python, MEL, MaxScript, Bash, PowerShell, and more.

🏆

Version-Aware Gateway Election

Multiple DCC instances compete for the gateway role. Newer adapters can take over cleanly while existing instances stay discoverable.

🦀

Rust-Powered Core

Zero third-party Python library dependencies. Packaged gateway daemon binary via dcc-mcp-server. Zero-copy IPC via Named Pipes and Unix Sockets. rmp-serde serialization. LZ4 shared memory. Sub-millisecond tool calls.

🔒

SkillPolicy & Scope

allow_implicit_invocation controls whether AI can call a skill without explicit load_skill. products filter visibility by DCC. Trust levels (repo < user < system < admin).

📦

Instance Tracking

Every DCC registers pid, display_name, active scene, and open documents. AI agents route to the right instance by document or display name.

🛡️

Sandbox & Audit Log

Policy-based access control with in-memory audit logging. Define what AI can and cannot do per DCC type.

🌐

MCP Streamable HTTP + REST

Built-in MCP server, REST /v1/* dynamic-capability surface, Admin UI, audit logs, traces, and gateway diagnostics.

📊

Structured Results

Every tool returns (success, message, context, next_steps). AI agents reason clearly about outcomes. No fragile text parsing.