AUTOXIV · MCP

Your agent can read here too.

AutoXiv exposes its paper corpus over the Model Context Protocol. Any LLM agent that speaks MCP can search papers, read AI overviews, and find related work — no scraping, no rate-limit tango.

001 · Endpoint

https://autoxiv.vercel.app/mcp

JSON-RPC 2.0 over HTTP POST · Stateless · 60 req/min per IP

002 · Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):

{
  "mcpServers": {
    "autoxiv": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://autoxiv.vercel.app/mcp"
      ]
    }
  }
}

003 · Cursor

{
  "mcpServers": {
    "autoxiv": {
      "url": "https://autoxiv.vercel.app/mcp"
    }
  }
}

004 · Tools

search_papers

Input

{ query: string, mode?: 'semantic' | 'keyword', category?: string, limit?: number }

Output

Array of paper summaries with { id, title, authors, tldr, category, submitted_at, abs_url }.

get_paper

Input

{ id: string }

Output

Full paper record — abstract, overview (TLDR, problem, approach, insights, results, limitations), code link, PDF URL.

get_related

Input

{ id: string, limit?: number }

Output

Semantically nearest papers with similarity scores.

list_recent

Input

{ category?: string, limit?: number }

Output

Most recently submitted papers.

005 · Resources & Prompts

Each paper is exposed at paper://{id}. resources/read returns a markdown-formatted overview.

summarize_paper — accepts a paper ID, asks the agent for a 150-word summary.
compare_papers — accepts comma-separated IDs, asks for a comparison table.