dsh-unreal-mcp
Run the following command in DeepSeek Harness:
dsh plugin install PeterTXPan/dsh-unreal-mcp
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install PeterTXPan/dsh-unreal-mcp in DeepSeek Harness to install this plugin, source at https://github.com/PeterTXPan/dsh-unreal-mcp
About this plugin
When working with Unreal Engine 5.8 and DeepSeek Harness, a recurring gap is a thin, purpose-built bridge that connects DSH's in-box MCP client to Epic's official Unreal MCP server without dragging in a full UE plugin, a DSH fork, or a general-purpose MCP protocol implementation. dsh-unreal-mcp fills exactly that gap: it reuses Unreal's ModelContextProtocol, ToolsetRegistry, and AllToolsets as-is, mounts DSH's MCP Client on top, and keeps the adapter layer deliberately small and single-responsibility.
Three bundled Unreal Skills drive the day-to-day workflow. unreal-mcp discovers and invokes toolsets already present in the editor; create-toolset guides the authoring of C++ or Python toolsets that an AI agent can call; unreal-skill walks you through creating UAgentSkill classes or project-level Skill assets registered inside the editor. Beyond skills, the adapter auto-detects each session's .uproject and UE source tree, injects a concise Unreal context into the system prompt, exposes a single loopback-only endpoint shared by both the context row and the MCP client row, and ships a read-only diagnostic that reports separate errors for a missing project, an unreachable endpoint, absent Tool Search meta-tools, and an empty toolset catalog.
It is built for engine developers practicing AI-agent workflows inside UE 5.8: install once through DSH, and the agent immediately understands project context, calls editor toolsets, authors new toolsets on demand, and pinpoints whether a failure lives in the connection layer or the editor layer, without you hand-rolling MCP glue code.
Use Cases
- Discover and invoke editor toolsets via DSH agent in UE 5.8
- Author AI-callable C++ or Python toolsets inside an Unreal project
- Diagnose the live MCP connection and toolset catalog between DSH and Unreal
Best For
- Engine developers building AI-agent workflows in Unreal Engine 5.8
- Teams leveraging DeepSeek Harness for UE project development
- Developers who need a lightweight MCP bridge without hand-rolling integration code
Related Plugins
A unified suite combining hot runtime injection, task-aware thinking-mode routing, and a graded session protocol with red-team gates to sustain model diligence across long-horizon inference.
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.