Command Palette

Search for a command to run...

UnylyUnyly
Browse all

Tashan SciSpark Research Assistant

FreeNot checked

Automates scientific research workflows by integrating arXiv and Google Scholar for paper discovery, employing collaborative AI analysis through Mixture of Agen

GitHubEmbed

About

Automates scientific research workflows by integrating arXiv and Google Scholar for paper discovery, employing collaborative AI analysis through Mixture of Agents approach to generate novel research hypotheses, comprehensive literature reviews, and complete paper drafts across multiple scientific domains.

README

Python文件和编码规约

  • .py 文件编码为 utf-8

Git 贡献提交规范

  • feat 增加新功能
  • fix 修复问题/BUG
  • style 代码风格相关无影响运行结果的
  • perf 优化/性能提升
  • refactor 重构
  • revert 撤销修改
  • test 测试相关
  • docs 文档/注释
  • chore 依赖更新/脚手架配置修改等
  • ci 持续集成
  • types 类型定义文件更改
  • wip 开发中

启动服务

启动 Celery Worker

方式一:使用优化启动脚本(推荐)

Windows系统:

# 直接运行批处理文件
start_celery_worker.bat

# 或使用Python脚本
python start_celery_worker.py

Linux/Mac系统:

python start_celery_worker.py

方式二:传统启动方式

python -m celery -A app.task.paper_assistant worker --pool=solo -l info

注意: 推荐使用方式一,它包含了内存优化配置,能够有效防止内存爆炸问题。

MCP工具异步任务支持

重要提醒: 当使用MCP工具中的异步功能(如研究想法生成)时,必须先启动Celery Worker:

# 启动Celery Worker以支持异步任务
python start_celery_worker.py

异步MCP工具包括:

  • generate_research_idea - 生成研究想法(需要Celery Worker支持)
  • get_task_status - 获取异步任务状态

如果未启动Celery Worker,异步MCP工具将无法正常工作。建议在使用MCP服务器前先启动Celery Worker。

from github.com/daiduo2/tashan_scispark_mcp

Installing Tashan SciSpark Research Assistant

This server has no published package — it is built from source. Open the repository and follow its README.

▸ github.com/daiduo2/tashan_scispark_mcp

FAQ

Is Tashan SciSpark Research Assistant MCP free?

Yes, Tashan SciSpark Research Assistant MCP is free — one-click install via Unyly at no cost.

Does Tashan SciSpark Research Assistant need an API key?

No, Tashan SciSpark Research Assistant runs without API keys or environment variables.

Is Tashan SciSpark Research Assistant hosted or self-hosted?

Self-hosted: the server runs locally on your machine via the install command above.

How do I install Tashan SciSpark Research Assistant in Claude Desktop, Claude Code or Cursor?

Open Tashan SciSpark Research Assistant on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.

Related MCPs

Compare Tashan SciSpark Research Assistant with

Not sure what to pick?

Find your stack in 60 seconds

Author?

Embed badge for your README

Browse similar

All ai MCPs