dcc-mcp/dcc-mcp-core — Core runtime and shared tooling for DCC-MCP: safe, skill-first MCP integration across Maya, Blender,…

Description and use

**Brief Summary**
dcc‑mcp‑core is the runtime and shared tooling that powers DCC‑MCP, a protocol for safe, “skill‑first” integration of AI assistants with major DCC applications such as Maya, Blender, Houdini, Photoshop, and custom hosts. Written in Rust, the library provides a unified API/SDK and CLI that lets developers expose tool‑specific capabilities to AI agents via the Model Context Protocol (MCP).

**Value**

• **Standardized bridge**: By abstracting the quirks of each DCC package behind a common MCP interface, developers can connect AI agents to real creative tools without writing bespoke adapters for every host.
• **Safety & control**: MCP’s “skill‑first” design lets you expose only vetted commands, reducing the risk of unintended actions by an AI assistant.
• **Cross‑tool portability**: The same integration code can be reused across Maya, Blender, Houdini, Photoshop, etc., accelerating multi‑tool pipelines and reducing maintenance overhead.

**Practical Adoption Path**

1. **Prototype** – Clone the repo, add the Rust crate to your project, and use the provided SDK to register a few simple commands (e.g., “export current scene”).
2. **MCP Server** – Deploy a Model Context Protocol server (bundled with the core) that exposes those commands to an AI agent (e.g., a LangChain or OpenAI‑based assistant).
3. **Iterate** – Extend the command set, map host‑specific APIs, and test with the CLI to verify correct signal flow.
4. **Productionize** – Containerize the MCP server, integrate it into your CI/CD pipeline, and enforce security policies (e.g., command whitelisting, authentication).

**Production Readiness**

• **Maturity**: Medium. The codebase is recent (last commit 2026‑06‑22), has modest community traction (≈28 ★), and is written in Rust, which offers safety and performance.
• **Strengths**: Clear API/SDK, CLI for rapid testing, and a well‑defined protocol that aligns with emerging AI‑tool integration standards.
• **Caveats**: Limited external adoption, few forks, and the need for a thorough security review (license compliance, dependency audit, and maintainer activity). Before shipping to customers, perform:
• Dependency vulnerability scanning,
• License verification,
• Load‑testing of the MCP server under realistic tool‑call volumes, and
• Implementation of authentication/authorization around exposed commands.

With those checks in place, dcc‑mcp‑core is a solid foundation for building AI‑augmented DCC workflows and can move from internal prototyping to production use.

Problem

dcc-mcp/dcc-mcp-core helps connect AI assistants to real tools and data through a standard protocol.

Outcome

Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.

Workflow

• connect AI agents to tools
• ship Model Context Protocol servers
• standardize integrations

Evidence

Core runtime and shared tooling for DCC-MCP: safe, skill-first MCP integration across Maya, Blender, Houdini, Photoshop, and custom DCC hosts.

Source