name: arxiv-mcp description: Search and retrieve academic papers from arXiv.org using WebFetch and Exa. No MCP server required - uses existing tools to access arXiv API directly. version: 2.0.0 model: sonnet invoked_by: both user_invocable: true tools: [WebFetch, mcp__Exa__web_search_exa]

No MCP server required - uses WebFetch + Exa

requires_mcp_server: false mcp_server_status: not_required

best_practices:

• Use specific search queries for better results
• Combine author and keyword searches when appropriate
• Use Exa for semantic search, WebFetch for specific paper IDs
• Check multiple related papers for comprehensive research error_handling: graceful streaming: supported

arXiv Search Skill

✅ No Installation Required

This skill uses existing tools to access arXiv:

• WebFetch - Direct access to arXiv API
• Exa - Semantic search with arXiv filtering

Works immediately - no MCP server, no restart needed.

Method 1: WebFetch with arXiv API (Recommended for specific queries)

The arXiv API is publicly accessible at http://export.arxiv.org/api/query.

Search by Keywords

WebFetch({
  url: 'http://export.arxiv.org/api/query?search_query=all:transformer+attention&max_results=10&sortBy=relevance',
  prompt: 'Extract paper titles, authors, abstracts, arXiv IDs, and PDF links from these results',
});

Search by Author

WebFetch({
  url: 'http://export.arxiv.org/api/query?search_query=au:LeCun&max_results=10&sortBy=submittedDate',
  prompt: 'Extract paper titles, authors, abstracts, and arXiv IDs',
});

Search by Category

WebFetch({
  url: 'http://export.arxiv.org/api/query?search_query=cat:cs.LG&max_results=15&sortBy=submittedDate',
  prompt: 'Extract paper titles, authors, abstracts, categories, and arXiv IDs',
});

Get Specific Paper by ID

WebFetch({
  url: 'http://export.arxiv.org/api/query?id_list=2301.07041',
  prompt:
    'Extract full details: title, all authors, abstract, categories, published date, PDF link',
});

API Query Parameters

Field Prefixes for search_query

Boolean Operators

Combine terms with AND, OR, ANDNOT:

search_query=ti:transformer+AND+abs:attention
search_query=au:LeCun+OR+au:Bengio
search_query=cat:cs.LG+ANDNOT+ti:survey

Method 2: Exa Search (Better for semantic/natural language queries)

Use Exa for more natural language queries with arXiv filtering:

Semantic Search

mcp__Exa__web_search_exa({
  query: 'site:arxiv.org transformer architecture attention mechanism deep learning',
  numResults: 10,
});

Recent Papers in a Field

mcp__Exa__web_search_exa({
  query: 'site:arxiv.org large language model scaling laws 2024',
  numResults: 15,
});

Author-Focused Search

mcp__Exa__web_search_exa({
  query: 'site:arxiv.org author:"Yann LeCun" deep learning',
  numResults: 10,
});

Common arXiv Categories

Workflow: Complete Research Process

Step 1: Initial Search

// Start with broad Exa search for semantic matching
mcp__Exa__web_search_exa({
  query: 'site:arxiv.org transformer attention mechanism neural networks',
  numResults: 10,
});

Step 2: Get Specific Papers

// Get details for interesting papers by ID
WebFetch({
  url: 'http://export.arxiv.org/api/query?id_list=2301.07041,2302.13971',
  prompt: 'Extract full metadata for each paper: title, authors, abstract, categories, PDF URL',
});

Step 3: Find Related Work

// Search by category of interesting paper
WebFetch({
  url: 'http://export.arxiv.org/api/query?search_query=cat:cs.LG+AND+ti:attention&max_results=10&sortBy=submittedDate',
  prompt: 'Find related papers, extract titles and abstracts',
});

Step 4: Get Recent Papers

// Latest papers in the field
WebFetch({
  url: 'http://export.arxiv.org/api/query?search_query=cat:cs.LG&max_results=20&sortBy=submittedDate&sortOrder=descending',
  prompt: 'Extract the 20 most recent machine learning papers',
});

</execution_process>

<best_practices>

1. Use Exa for discovery: Natural language queries find semantically related papers
2. Use WebFetch for precision: Specific IDs, categories, or API queries
3. Combine approaches: Exa to discover, WebFetch to deep-dive
4. Use specific queries: "transformer attention mechanism" > "machine learning"
5. Check multiple categories: Papers often span cs.AI + cs.LG + cs.CL
6. Sort by date for recent work: sortBy=submittedDate&sortOrder=descending

</best_practices> </instructions>

WebFetch({
  url: 'http://export.arxiv.org/api/query?search_query=ti:transformer+AND+abs:attention&max_results=10&sortBy=relevance',
  prompt: 'Extract paper titles, authors, abstracts, and arXiv IDs',
});

Example 2: Find papers by researcher:

WebFetch({
  url: 'http://export.arxiv.org/api/query?search_query=au:Vaswani&max_results=15',
  prompt: 'List all papers by this author with titles and dates',
});

Example 3: Get recent ML papers:

WebFetch({
  url: 'http://export.arxiv.org/api/query?search_query=cat:cs.LG&max_results=20&sortBy=submittedDate&sortOrder=descending',
  prompt: 'Extract the 20 most recent machine learning papers with titles and abstracts',
});

Example 4: Semantic search with Exa:

mcp__Exa__web_search_exa({
  query: 'site:arxiv.org multimodal large language models vision 2024',
  numResults: 10,
});

Example 5: Get specific paper details:

WebFetch({
  url: 'http://export.arxiv.org/api/query?id_list=1706.03762',
  prompt: "Extract complete details for the 'Attention Is All You Need' paper",
});

</usage_example> </examples>

Agent Integration

This skill is automatically assigned to:

• researcher - Academic research, literature review
• scientific-research-expert - Deep scientific analysis
• developer - Finding technical papers for implementation

Memory Protocol (MANDATORY)

Before starting:

cat .claude/context/memory/learnings.md

After completing:

• New pattern -> .claude/context/memory/learnings.md
• Issue found -> .claude/context/memory/issues.md
• Decision made -> .claude/context/memory/decisions.md

ASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.