alone-tree/dsh-skill-mcp-manager ↗★ 0
dsh-skill-mcp-manager
能力库 (Capability) — one-stop visual management of DSH Skills & MCP: on-demand MCP loading, in-session hot reload, and SKILL/MCP descriptions viewable in the plugin.
安装
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:alone-tree/dsh-skill-mcp-manager说明文档
阅读完整 README ↗Usage
In the UI
Open Settings → Capability:
- SKILL tab — every managed skill (bundle
SKILL.md), sorted by path: model-visibility switch, open in system editor, cross-platform delete. Skills shipped with the deployment (undernode_modules/app.asar) are read-only: view + open only. - MCP tab — every registered server with tier badges, tool counts and connection state: switch tier, inspect details (command / env / headers / tools), mask or reveal secrets, load / peek / disconnect, delete entries. A setting row adjusts the catalog's tool-description truncation (default 150 chars).
Model-facing tools
The plugin provides three small, fixed tools to manage all on-demand MCPs.
-
mcp_register— add or modify an MCP entry. Trial-connects (30s) + lists tools, then persists; the server's own description / version / title / website / instructions are captured automatically. Reuse it to change tier / parameters / notes; only connection-contract changes re-connect.mcp_register { name, tier?, transport, command?, args?, env?, cwd?, url?, headers?, notes? }tier∈eager|on-demand|disabled(defaulton-demand).notesis user-maintained and is not overwritten by developer MCP updates. -
mcp_load { name, peek? }— load / hot-reload a server, returns full tool definitions + server-declared metadata.peek: trueonly reads the snapshot — no connect, no disconnect — handy when the AI forgot a tool's parameters and wants a quick peek without interrupting the MCP's live process. Especially friendly for stateful MCPs like browser automation. -
mcp_call { name, tool, args? }— invoke an on-demand tool (mustmcp_loadfirst). Structuredargsonly — never shell text, never a temp file.