# dsh-web-mcp

> dsh-web-mcp — cv588888888888888888888ju-dsh-web-mcp. Use this tool when you need to manage workspaces, create or resume sessions, and interact with the DeepSeek Harness web UI from any MCP client. It solves problems of remote session management and messaging by exposing the cordis RPC API as stdio tools, accepting RPC requests as input and producing session stats and messages as output. This enables seamless integration and control of DSH sessions in various contexts, such as automated workflows or command-line interfaces.

Canonical page: https://skillsregistry.net/skills/cv588888888888888888888ju-dsh-web-mcp  
JSON: https://api.skillsregistry.net/v1/skills/cv588888888888888888888ju-dsh-web-mcp

## Description

An MCP bridge that exposes DeepSeek Harness (DSH) web UI's cordis RPC API as stdio tools, enabling any MCP client to manage workspaces, create/resume sessions, send messages, and fetch session stats.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** api-integration
- **Updated:** 2026-08-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/xvuauj7y2k)
- **Repository:** <https://github.com/cv588888888888888888888ju/dsh-web-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "cv588888888888888888888ju-dsh-web-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cv588888888888888888888ju-dsh-web-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cv588888888888888888888ju-dsh-web-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt