# Paper Search (arXiv + Semantic Scholar + OpenAlex)

> Paper Search (arXiv + Semantic Scholar + OpenAlex) — kangletian-paper-mcp. Use this tool when you need to efficiently search and retrieve academic papers from multiple sources, such as arXiv, Semantic Scholar, and OpenAlex. It solves problems of duplicated results and inconsistent rankings by de-duplicating and re-ranking papers, and provides additional features like citation graphs and author metrics. With a simple interface that takes search queries as input and returns relevant papers, citations, and metrics as output, this tool is ideal for AI agents requiring comprehensive academic paper search capabilities.

Canonical page: https://skillsregistry.net/skills/kangletian-paper-mcp  
JSON: https://api.skillsregistry.net/v1/skills/kangletian-paper-mcp

## Description

Unified academic paper search for AI agents. search_all queries arXiv, Semantic Scholar and OpenAlex at once, de-duplicates the same work across corpora (by DOI/title) and re-ranks with Reciprocal Rank Fusion so papers found by several sources rank highest. read_paper returns full arXiv text with formulas as LaTeX. Plus citation graphs, author metrics (h-index), recommendations and full-text snippet search across 220M+ papers. Remote streamable-HTTP, no auth required.

## Trust

- **Trust score (0–1):** 0.71
- **Verification tier:** verified
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/kangletian/paper-mcp)
- **Repository:** <https://github.com/MCPServings/paper-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "kangletian-paper-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kangletian-paper-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kangletian-paper-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt