asta-skill MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

Eight Semantic Scholar tools via MCP (get_paper, search_papers_by_relevance, get_citations, snippet_search, ...)
Intent→tool decision table so Claude picks the right function
Workflow patterns to avoid context-blow-up pitfalls (fields=citations warning baked in)
Batch operations for efficiency (get_paper_batch)
Works across Claude Code / Codex / Cursor / Windsurf / OpenClaw

라이브 데모

실제 사용 모습

asta-skill.replay ▶ 준비됨

0/0

설치

클라이언트 선택

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

{
  "mcpServers": {
    "asta-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Agents365-ai/asta-skill",
        "~/.claude/skills/asta-skill"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "asta-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Agents365-ai/asta-skill",
        "~/.claude/skills/asta-skill"
      ],
      "_inferred": true
    }
  }
}

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

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "asta-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Agents365-ai/asta-skill",
        "~/.claude/skills/asta-skill"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "asta-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Agents365-ai/asta-skill",
        "~/.claude/skills/asta-skill"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "asta-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Agents365-ai/asta-skill",
        "~/.claude/skills/asta-skill"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "asta-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/Agents365-ai/asta-skill",
          "~/.claude/skills/asta-skill"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add asta-skill -- git clone https://github.com/Agents365-ai/asta-skill ~/.claude/skills/asta-skill

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

사용 사례

실전 활용법: asta-skill

Run a literature review on a specific research question

👤 Grad students and researchers ⏱ ~60 min intermediate

언제 쓸까: You have a question and want to quickly map the relevant papers, not wade through Google Scholar.

사전 조건

Skill cloned — git clone https://github.com/Agents365-ai/asta-skill ~/.claude/skills/asta-skill
Ai2 Asta MCP server reachable — Follow Asta MCP setup; the skill assumes the MCP is configured

흐름

Kick off the search

Use asta-skill — find highly-cited papers on retrieval-augmented generation from 2023-2024.✓ 복사됨

→ Claude calls search_papers_by_relevance with good filters, not a generic query
Walk the citation graph

For the top 3, show me what cited them since.✓ 복사됨

→ get_citations calls with appropriate filtering
Pull evidence snippets

Extract a 500-word passage from each paper explaining their main evaluation method.✓ 복사됨

→ snippet_search returns targeted passages

결과: A mapped review with citation chains and evidence snippets — not just titles.

함정

Requesting fields=citations bulk-returns megabytes — The skill warns against this — trust the guidance and paginate instead

함께 쓰기: planning-with-files

Find a researcher's key papers and trace their influence

👤 Anyone profiling a potential collaborator or advisor ⏱ ~20 min beginner

언제 쓸까: You want a fast, accurate view of someone's publication record.

흐름

Resolve the author

asta-skill — find the author 'Jane Smith' who works on graph neural networks.✓ 복사됨

→ search_authors_by_name with disambiguation
Fetch papers

Get their papers sorted by citation count.✓ 복사됨

→ get_author_papers call with sort
Impact snapshot

For the top 3, who's cited them most and is building on the work?✓ 복사됨

→ Citation traversal showing ongoing lineage

결과: A one-page profile of a researcher's impact.

조합

다른 MCP와 조합해 10배 효율

asta-skill + planning-with-files

Literature reviews span days — persist findings.md and next-reads.md

Use planning-with-files — findings.md for papers read, next-reads.md for the queue.✓ 복사됨

asta-skill + filesystem

Save extracted snippets as notes in your Obsidian vault

For each paper, save the snippet to ~/obsidian/papers/<title>.md.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
search_papers_by_relevance	query + filters	Starting a literature search from a question	1 MCP call
get_paper / get_paper_batch	id or [ids]	Need full metadata on a known paper or list	1 MCP call (batch saves round-trips)
get_citations	paper id + filters + pagination	Walking citation graph forward	1 MCP call
snippet_search	paper id + query	Need evidence-level passages to ground claims	1 MCP call
search_authors_by_name / get_author_papers	name + disambiguators	Profiling a researcher	1 MCP call

비용 및 제한

운영 비용

API 쿼터: Semantic Scholar API limits via Asta MCP — check Ai2's current terms
호출당 토큰: Varies; fields=citations can blow up context so avoid it
금액: Free — skills are local files; Asta MCP itself is free for research use
팁: Prefer batch calls and paginated citation fetches; snippet_search beats fetching full bodies.

보안

권한, 시크릿, 파급범위

자격 증명 저장: No credentials in the skill. Asta MCP setup may involve API keys.

데이터 외부 송신: Queries go to Semantic Scholar via the Asta MCP server

문제 해결

자주 발생하는 오류와 해결

Skill not invoked — Claude does a web search instead of calling Asta

Say 'use asta-skill' explicitly; academic tasks alone don't always route to MCP.

확인: ls ~/.claude/skills/asta-skill/SKILL.md

SKILL.md frontmatter wrong

Re-clone; the description is what triggers auto-activation.

확인: head ~/.claude/skills/asta-skill/SKILL.md

Wrong trigger keywords — context blows up on citation fetch

Don't request fields=citations — paginate with get_citations and filters.

대안

asta-skill 다른 것과 비교

대안	언제 쓰나	단점/장점
arxiv MCP	You only need preprints, not cross-source citation graphs	Narrower source; no citation traversal
Raw Google Scholar	Quick one-off lookups without MCP setup	No structured tools, scraping-ish

asta-skill