Is the deepseek-harness-genui MCP server actively maintained?

The deepseek-harness-genui MCP server was last committed 20d ago and has 3 contributors. Issue health: 88% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

deepseek-harness-genui MCP Server

Name: pengyue-polaron/deepseek-harness-genui
Rating: 4.1 (1 reviews)
Author: pengyue-polaron

pengyue-polaron/deepseek-harness-genui

Score: 78.3 ↓ 3.6% Rank #2341 MCP Server

[![AgentRank](https://agentrank-ai.com/api/v1/badge/pengyue-polaron--deepseek-harness-genui)](https://agentrank-ai.com/tool/pengyue-polaron--deepseek-harness-genui/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

Are you the maintainer of pengyue-polaron/deepseek-harness-genui? Claim this listing →

Task-specific React apps for DeepSeek Harness with state carried into the next Agent turn

Add AgentRank to Claude Code Discover and compare tools like pengyue-polaron/deepseek-harness-genui — your AI finds the right one automatically

Get API Access →

claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

pengyue-polaron/deepseek-harness-genui is a TypeScript tool licensed under MIT. Task-specific React apps for DeepSeek Harness with state carried into the next Agent turn Topics: deepseek-harness, dsh, dsh-plugin, generative-ui, genui, mcp, react.

Ranked #2341 out of 24846 indexed tools.

In the top 10% of all indexed tools.

Ecosystem

TypeScript MIT

deepseek-harnessdshdsh-plugingenerative-uigenuimcpreact

Score Breakdown

Stars 15% 116

116 stars → growing community

Freshness 25% 20d ago

Last commit 20d ago → recently updated

Issue Health 25% 88%

7/8 issues closed → responsive maintainer

Contributors 10% 3

3 contributors → small team

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads N/A

Forks 13

Description Good

License MIT

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

Markdown

[![AgentRank](https://agentrank-ai.com/api/v1/badge/pengyue-polaron--deepseek-harness-genui)](https://agentrank-ai.com/tool/pengyue-polaron--deepseek-harness-genui/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

<a href="https://agentrank-ai.com/tool/pengyue-polaron--deepseek-harness-genui/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/pengyue-polaron--deepseek-harness-genui" alt="AgentRank"></a>

Embed Widget docs →

HTML

<script src="https://agentrank-ai.com/embed.js" data-tool="pengyue-polaron/deepseek-harness-genui"></script>

Details

Stars: 116
Forks: 13
Open Issues: 1
Closed Issues: 7
Contributors: 3
Dependents: —
Language: TypeScript
License: MIT
Last Commit: 20d ago

Matched Queries

topic:mcp

From the README

# DeepSeek Harness GenUI

English | [简体中文](README.zh-CN.md)

DeepSeek Harness GenUI lets an Agent build a focused interface when a task is awkward in text. The Coding Agent writes ordinary React + TypeScript—not a component-tree DSL—and the interface can save user selections for the next Agent turn.

The result is a task-specific app that can explain a difficult relationship, collect connected choices, or continue a tool-backed workflow without asking the user to repeat their input.

Related research: [*EvoGenUI-Bench: Evaluating LLMs as Multi-Turn Generative UI Assistants*](https://arxiv.org/abs/2608.29387).

## Install

Requires Node.js `^22.19.0 || ^24.0.0` and a supported DeepSeek Harness Web profile.

```sh
dsh plugin --profile web add dsh-plugin-genui
dsh --profile web
```

v0.15 supports Inline, Canvas, fullscreen, and localhost on the tested Harness versions listed in the [release notes](docs/release-notes-v0.15.1.md). TUI/headless profiles are not supported. The local compiler

Read full README on GitHub →