scientific-agent-skills MCP — Сценарии использования, Установка & Живое демо

Зачем использовать

Ключевые функции

133 skills spanning genomics, cheminformatics, molecular dynamics, clinical trials, ML training, and paper writing
REST API access recipes for 78+ public databases (ClinVar, COSMIC, ClinicalTrials.gov, FDA, PubMed, bioRxiv, arXiv)
Each skill includes runnable code examples and links to primary documentation
Claude routes between skills automatically based on the task domain

Живое демо

Как выглядит на практике

scientific-agent-skill.replay ▶ готово

0/0

Установка

Выберите клиент

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "scientific-agent-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/K-Dense-AI/scientific-agent-skills",
        "~/.claude/skills/scientific-agent-skills"
      ],
      "_inferred": true
    }
  }
}

Откройте Claude Desktop → Settings → Developer → Edit Config. Перезапустите после сохранения.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "scientific-agent-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/K-Dense-AI/scientific-agent-skills",
        "~/.claude/skills/scientific-agent-skills"
      ],
      "_inferred": true
    }
  }
}

Cursor использует ту же схему mcpServers, что и Claude Desktop. Конфиг проекта приоритетнее глобального.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "scientific-agent-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/K-Dense-AI/scientific-agent-skills",
        "~/.claude/skills/scientific-agent-skills"
      ],
      "_inferred": true
    }
  }
}

Щёлкните значок MCP Servers на боковой панели Cline, затем "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "scientific-agent-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/K-Dense-AI/scientific-agent-skills",
        "~/.claude/skills/scientific-agent-skills"
      ],
      "_inferred": true
    }
  }
}

Тот же формат, что и Claude Desktop. Перезапустите Windsurf для применения.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "scientific-agent-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/K-Dense-AI/scientific-agent-skills",
        "~/.claude/skills/scientific-agent-skills"
      ]
    }
  ]
}

Continue использует массив объектов серверов, а не map.

~/.config/zed/settings.json

{
  "context_servers": {
    "scientific-agent-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/K-Dense-AI/scientific-agent-skills",
          "~/.claude/skills/scientific-agent-skills"
        ]
      }
    }
  }
}

Добавьте в context_servers. Zed перезагружается автоматически.

claude mcp add scientific-agent-skill -- git clone https://github.com/K-Dense-AI/scientific-agent-skills ~/.claude/skills/scientific-agent-skills

Однострочная команда. Проверить: claude mcp list. Удалить: claude mcp remove.

Сценарии использования

Реальные сценарии: scientific-agent-skills

Run a single-cell RNA-seq analysis with Scanpy

👤 Computational biologists and bioinformatics postdocs ⏱ ~30 min intermediate

Когда использовать: You have an .h5ad file and want QC, clustering, and UMAP without re-reading the Scanpy docs.

Предварительные требования

Scanpy installed in your env — pip install scanpy
An .h5ad dataset — Download from a public repo or use your own

Поток

Tell Claude the data and the goal

I have pbmc3k.h5ad. Use the scanpy skill to do QC, normalization, clustering, and a UMAP. Explain each step.✓ Скопировано

→ Claude calls the right Scanpy functions in the right order with sensible defaults
Iterate on parameters

Re-do clustering with resolution 0.8 and show how cluster labels changed.✓ Скопировано

→ Parameter tweak without re-planning the full pipeline

Итог: A reproducible notebook plus figures, using idiomatic Scanpy — no hallucinated function names.

Подводные камни

Generic ML advice from Claude that ignores domain conventions — Reference the skill by name: 'use the scanpy skill'

Сочетать с: filesystem

Build a structured literature review from PubMed + arXiv

👤 PhD students, research scientists ⏱ ~45 min intermediate

Когда использовать: You need 30+ papers on a topic with abstracts and citation metadata, not just titles from Google.

Поток

Specify scope

Use the paper-lookup skill. Find all PubMed and bioRxiv papers on GLP-1 agonists for Alzheimer's in the last 3 years.✓ Скопировано

→ Claude hits the right APIs with correct query syntax
Cluster by theme

Cluster by hypothesis (neuroinflammation, vascular, direct neuronal) and give me the top 3 papers per cluster.✓ Скопировано

→ Thematic grouping with citation-ready metadata

Итог: A reviewable literature map with real DOIs, not fabricated citations.

Подводные камни

Claude hallucinates paper titles without the skill — Always verify DOIs — have Claude fetch one record to prove it's real

Сочетать с: fetch

Dock a small molecule to a target protein with DiffDock

👤 Medicinal chemists, drug discovery researchers ⏱ ~20 min advanced

Когда использовать: You have a SMILES string and a PDB target and want a quick first-pass pose prediction.

Предварительные требования

DiffDock environment — Follow the DiffDock skill's env-setup recipe

Поток

Provide ligand and receptor

Using the diffdock skill, dock SMILES 'CC(=O)OC1=CC=CC=C1C(=O)O' into PDB 1ABC. Give me the top 5 poses with scores.✓ Скопировано

→ Claude runs the right DiffDock command with correct flags
Visualize

Generate a PyMOL script to render the top pose.✓ Скопировано

→ Runnable .pml file

Итог: Pose predictions ready to feed into a downstream free-energy calculation.

Подводные камни

Claude invents flags that don't exist in DiffDock — The skill's reference folder has the real CLI — insist Claude consult it

Сочетать с: filesystem

Комбинации

Сочетайте с другими MCP — эффект x10

scientific-agent-skill + filesystem

Skills produce notebooks and figures; filesystem MCP stores and organizes the output

Save the Scanpy UMAP to results/figures/ and write a README for the experiment.✓ Скопировано

scientific-agent-skill + arxiv

Pair the paper-lookup skill with the arxiv MCP for richer citation graphs

Find arXiv papers citing the one I just read, grouped by which section they cite.✓ Скопировано

Инструменты

Что предоставляет этот MCP

Инструмент	Входные данные	Когда вызывать	Стоимость
Bioinformatics (BioPython, Scanpy, pysam, gget, scVelo)	sequence / count matrix / BAM file	Sequence, genomics, or single-cell workflow	0 — local compute
Cheminformatics (RDKit, Datamol, DeepChem, DiffDock, OpenMM)	SMILES / PDB / MOL2	Small molecule, protein structure, or dynamics problem	0
Clinical databases (ClinVar, COSMIC, ClinicalTrials.gov, FDA)	gene / variant / trial ID	Looking up clinical evidence or trial status	0 — public APIs
Paper lookup (PubMed, bioRxiv, arXiv)	query string, date range	Literature search with real citations	0
ML training (PyTorch Lightning, Transformers, PyMC, TimesFM)	dataset + config	Building a model with idiomatic framework usage	0

Стоимость и лимиты

Во что обходится

Квота API: Public databases (NCBI, PubMed) have their own polite-use limits — typically 3 req/s
Токенов на вызов: SKILL.md references are sizeable; expect 2-5k tokens loaded per domain touched
Деньги: Free — skills are local files; only pay for compute you run
Совет: Scope the prompt to one domain at a time so Claude doesn't load every SKILL.md.

Безопасность

Права, секреты, радиус поражения

Хранение учётных данных: No credentials in the skill itself; NCBI/PubMed work better with an email-in-env-var for polite rate limiting

Исходящий трафик: Only to the public science APIs you choose to query

Clinical data skills can hit PHI-adjacent records — make sure your usage complies with IRB/HIPAA when applicable.

Устранение неполадок

Частые ошибки и исправления

Claude uses wrong function name from a skill's library

Tell it to re-read the skill's reference folder; the SKILL.md frontmatter should auto-load it.

Проверить: ls ~/.claude/skills/scientific-agent-skills/<skill>/references/

API rate limit hit on NCBI

Add an email to NCBI_EMAIL env var and cap concurrency at 3 req/s.

Skill not invoked on a relevant prompt

Mention the library name explicitly ('use the rdkit skill') — auto-invocation is fuzzy across 133 skills.

Альтернативы

scientific-agent-skills в сравнении

Альтернатива	Когда использовать	Компромисс
ai-research-skill (Orchestra-Research)	You want ML-research infrastructure (training, distributed, inference) rather than wet-lab / clinical	More ML systems, less biology / chemistry domain depth
biomcp	You want an MCP server (live tools) rather than prompt-bundle skills	MCPs execute calls; skills just teach Claude to write the right code

Ещё

Ресурсы

📖 Читать официальный README на GitHub

🐙 Открытые задачи

🔍 Все 400+ MCP-серверов и Skills