SciAgent-Skills MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

197 specialized life-science skills
Coverage: RNA-seq, single-cell (scRNA), drug discovery, proteomics, variant calling
BixBench accuracy 92.0% — higher than generic agents
Canonical tool invocation (samtools, bcftools, salmon, scanpy, Seurat, etc.)
Reproducibility patterns (conda/mamba envs, config files)
Powers OmicsHorizon platform

라이브 데모

실제 사용 모습

sciagent-skill.replay ▶ 준비됨

0/0

설치

클라이언트 선택

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

{
  "mcpServers": {
    "sciagent-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/jaechang-hits/SciAgent-Skills",
        "~/.claude/skills/SciAgent-Skills"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "sciagent-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/jaechang-hits/SciAgent-Skills",
        "~/.claude/skills/SciAgent-Skills"
      ],
      "_inferred": true
    }
  }
}

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

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "sciagent-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/jaechang-hits/SciAgent-Skills",
        "~/.claude/skills/SciAgent-Skills"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "sciagent-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/jaechang-hits/SciAgent-Skills",
        "~/.claude/skills/SciAgent-Skills"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "sciagent-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/jaechang-hits/SciAgent-Skills",
        "~/.claude/skills/SciAgent-Skills"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "sciagent-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/jaechang-hits/SciAgent-Skills",
          "~/.claude/skills/SciAgent-Skills"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add sciagent-skill -- git clone https://github.com/jaechang-hits/SciAgent-Skills ~/.claude/skills/SciAgent-Skills

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

사용 사례

실전 활용법: SciAgent-Skills

How to run a bulk RNA-seq differential expression analysis

👤 Biologists and bioinformaticians with FASTQ files and a need for DE results ⏱ ~120 min advanced

언제 쓸까: You have paired-end FASTQ, a reference, and a condition table.

사전 조건

Skill installed — git clone https://github.com/jaechang-hits/SciAgent-Skills ~/.claude/skills/sciagent-skills
Conda/mamba + compute — Use a Linux server or HPC; macOS fine for small datasets

흐름

Plan the pipeline

Plan a bulk RNA-seq DE workflow for 2 conditions x 3 reps with salmon + tximport + DESeq2. Output expected files per step.✓ 복사됨

→ Step list with tools and intermediate outputs
Run quantification

Run salmon quant for each sample; produce a script.✓ 복사됨

→ Bash script with salmon invocations
DE analysis

Load quants via tximport, run DESeq2, produce MA + volcano plots and a top-50 gene table.✓ 복사됨

→ R script + output files

결과: A DE table + plots you can hand to a PI or collaborator.

함정

Mis-matched reference versus annotation GTF — Check release numbers explicitly; salmon and DESeq2 can silently run on mismatched IDs
Low-count filtering removes biological signal — Use independent filtering or raise threshold gradually; don't blanket filter

Single-cell RNA-seq QC and clustering baseline

👤 Researchers starting scRNA analysis from 10x output ⏱ ~90 min advanced

언제 쓸까: You have a cellranger output directory and need a first-pass Seurat or Scanpy analysis.

흐름

Load + QC

Load 10x data from cellranger output, do QC (pct.mt, counts, features), filter, normalize.✓ 복사됨

→ QC plots + filtered object
Cluster

Run PCA, find neighbors, cluster at resolution 0.5, and UMAP.✓ 복사됨

→ Cluster labels + UMAP plot
Marker genes

Find cluster markers, produce a top-5-per-cluster heatmap.✓ 복사됨

→ Marker table + heatmap

결과: An annotated UMAP and marker table ready for biological interpretation.

함정

Over-clustering at the default resolution — Try a sweep 0.2-1.0 and pick based on silhouette + biological plausibility

Germline variant calling from WGS

👤 Genomics teams calling SNPs and indels ⏱ ~180 min advanced

언제 쓸까: You have aligned BAMs and need a VCF using best-practices (GATK).

흐름

Plan pipeline

Plan GATK best-practices germline pipeline from aligned BAMs: BQSR, HaplotypeCaller, joint genotyping with GenomicsDBImport.✓ 복사됨

→ Pipeline outline with expected runtimes
Generate scripts

Produce Snakemake rules for each step.✓ 복사됨

→ Snakefile with rules and config

결과: A reproducible Snakemake pipeline ready to run on your cluster.

함정

Skipping BQSR on small cohorts — Still do it — GATK's downstream filters assume recalibrated quality scores

Triage small-molecule hits from a screen

👤 Med-chem groups triaging HTS results ⏱ ~60 min advanced

언제 쓸까: You have a hit list and want to rank by drug-likeness + novelty.

흐름

Filter by Lipinski + PAINS

Compute Lipinski and PAINS flags on this SMILES list, output a filtered table.✓ 복사됨

→ RDKit-based script + filtered CSV
Similarity to known drugs

For remaining hits, compute Tanimoto similarity to ChEMBL approved drugs; flag >0.85 as known-scaffold.✓ 복사됨

→ Similarity table with flags

결과: A triaged hit list prioritized for follow-up.

조합

다른 MCP와 조합해 10배 효율

sciagent-skill + filesystem

Read local FASTQ/BAM files and have SciAgent plan the analysis pipeline on actual data

List the FASTQ files in ~/data/rnaseq/, then use SciAgent to plan a salmon + DESeq2 pipeline for these samples.✓ 복사됨

sciagent-skill + github

Search nf-core or Bioconductor repos for reference implementations, then adapt with SciAgent

Search nf-core/rnaseq on GitHub for how they handle trimming, then use SciAgent to adapt that step for my pipeline.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
Bulk RNA-seq workflow	FASTQ + design	Standard DE analysis	compute
scRNA-seq workflow	10x output	Single-cell baseline	compute
Variant calling	BAMs	WGS/WES cohorts	compute
Proteomics analysis	MS data	MS-based proteomics	compute
Drug discovery triage	SMILES list	Hit triage	compute

비용 및 제한

운영 비용

API 쿼터: None at skill level
호출당 토큰: 10-50k per pipeline design
금액: Free skills; compute costs depend on dataset size
팁: Plan the pipeline as a script first, then run; don't keep Claude in the loop during long compute.

보안

권한, 시크릿, 파급범위

자격 증명 저장: No credentials

데이터 외부 송신: Pipeline designs and snippets go to Claude. Actual patient data should stay on HIPAA-compliant compute.

Do not paste patient identifiers or raw sequence data that could be re-identified into prompts.
Always review generated variant-calling parameters — wrong caller settings can produce misleading results.

문제 해결

자주 발생하는 오류와 해결

tximport fails on missing transcript-to-gene mapping

Regenerate tx2gene from the same GTF you used for the salmon index; mismatch is the usual cause.

Seurat object too large for available RAM

Subsample or switch to on-disk storage with BPCells or DelayedArray-backed Seurat

Conda environment conflicts during pipeline setup

Use mamba instead of conda for faster resolution; pin exact versions in environment.yml rather than floating constraints

확인: mamba env create -f environment.yml --dry-run

Generated script references wrong genome build (hg19 vs hg38)

Explicitly state the genome build in your first prompt; SciAgent defaults may not match your data

대안

SciAgent-Skills 다른 것과 비교

대안	언제 쓰나	단점/장점
Galaxy / nf-core	You want audited, community pipelines rather than LLM-generated scripts	Less conversational; slower to customize

SciAgent-Skills