scientific-agent-skills MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

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

라이브 데모

실제 사용 모습

scientific-agent-skill.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/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
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.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
    }
  }
}

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

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
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.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
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.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"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.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"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

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

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: scientific-agent-skills

Run a single-cell RNA-seq analysis with Scanpy

👤 Computational biologists and bioinformatics postdocs ⏱ ~30 min intermediate

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

사전 조건

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

흐름

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.✓ 복사됨

→ 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.✓ 복사됨

→ Parameter tweak without re-planning the full pipeline

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

함정

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

함께 쓰기: filesystem

Build a structured literature review from PubMed + arXiv

👤 PhD students, research scientists ⏱ ~45 min intermediate

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

흐름

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.✓ 복사됨

→ 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.✓ 복사됨

→ Thematic grouping with citation-ready metadata

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

함정

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

함께 쓰기: fetch

Dock a small molecule to a target protein with DiffDock

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

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

사전 조건

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

흐름

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.✓ 복사됨

→ Claude runs the right DiffDock command with correct flags
Visualize

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

→ Runnable .pml file

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

함정

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

함께 쓰기: filesystem

조합

다른 MCP와 조합해 10배 효율

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.✓ 복사됨

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.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
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

비용 및 제한

운영 비용

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

보안

권한, 시크릿, 파급범위

자격 증명 저장: No credentials in the skill itself; NCBI/PubMed work better with an email-in-env-var for polite rate limiting

데이터 외부 송신: 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.

문제 해결

자주 발생하는 오류와 해결

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.

확인: 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.

대안

scientific-agent-skills 다른 것과 비교

대안	언제 쓰나	단점/장점
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

scientific-agent-skills

왜 쓰나요

핵심 기능

라이브 데모

실제 사용 모습

설치

클라이언트 선택

사용 사례

실전 활용법: scientific-agent-skills

Run a single-cell RNA-seq analysis with Scanpy

사전 조건

흐름

함정

Build a structured literature review from PubMed + arXiv

흐름

함정

Dock a small molecule to a target protein with DiffDock

사전 조건

흐름

함정

조합

다른 MCP와 조합해 10배 효율

도구

이 MCP가 노출하는 것

비용 및 제한

운영 비용

보안

권한, 시크릿, 파급범위

문제 해결

자주 발생하는 오류와 해결

대안

scientific-agent-skills 다른 것과 비교

더 보기

리소스