# Paperswithcode

> Paperswithcode is a freemium MCP server for academic research. Gateway pack that searches ML papers and finds linked code via Hugging Face Papers. It can run locally on your machine or as a hosted remote server.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Starting price:** $49 a month
- **Platforms:** API, CLI, self-hosted
- **Website:** https://pipeworx.io/packs/paperswithcode
- **Repository:** https://github.com/pipeworx-io/mcp-paperswithcode
- **MCP Registry name:** io.github.pipeworx-io/paperswithcode
- **Categories:** [academic research](https://ai-powered.com/categories/academic-research)
- **Listing updated:** 2026-11-18

## About

The README says this server is an unofficial integration that exposes four tools for machine-learning research papers, backed by Hugging Face Papers, which replaced the original Papers with Code service. You can search papers, pull trending lists for a given day, fetch detail for an arXiv id, and look up implementations such as a linked GitHub repository and related Hugging Face models, datasets and demo Spaces.

The server runs through the Pipeworx MCP gateway, either as a remote streamable-HTTP endpoint or as a local npm stdio bridge that forwards calls to it. The site says anonymous calls are capped daily and that a free account raises the limit, with paid tiers for higher volume.

It suits researchers and developers who want an AI client to look up recent papers and their code without leaving the conversation. Note that the tool list also includes shared gateway meta-tools beyond the four pack-specific ones.

## Features

- **Paper search:** Searches ML and AI papers and returns arXiv id, title, authors, upvotes and a linked GitHub repo when available.
- **Trending papers:** Lists the day's trending ML papers ranked by community upvotes, with an optional date.
- **Paper detail lookup:** Returns abstract, AI-generated summary, keywords and counts of linked models, datasets and Spaces for an arXiv id.
- **Implementation finder:** Lists the linked GitHub repository plus related Hugging Face models, demo Spaces and datasets for a paper.
- **Flexible connection options:** Connects over remote streamable HTTP or a local npx stdio bridge, with an optional API key for higher daily limits.

## Good for

- Find recent papers on a specific ML topic
- Check what the hottest AI papers are this week
- Locate a reference implementation for an arXiv paper
- Find pretrained models or datasets linked to a research paper

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http paperswithcode https://gateway.pipeworx.io/paperswithcode/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://gateway.pipeworx.io/paperswithcode/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "paperswithcode": {
      "url": "https://gateway.pipeworx.io/paperswithcode/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "paperswithcode": {
      "type": "http",
      "url": "https://gateway.pipeworx.io/paperswithcode/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "paperswithcode": {
      "serverUrl": "https://gateway.pipeworx.io/paperswithcode/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "paperswithcode": {
      "type": "http",
      "url": "https://gateway.pipeworx.io/paperswithcode/mcp"
    }
  }
}
```

## Tools

- `search_papers`: Search machine-learning / AI research papers via Hugging Face Papers, returning arXiv id, title, authors, upvotes and a linked GitHub repo when available.
- `trending_papers`: Today's trending ML/AI papers (or a given day's), ranked by community upvotes.
- `get_paper`: Full detail for a paper by arXiv id, including abstract, summary, keywords and linked resource counts.
- `get_repositories`: Linked GitHub repository plus popular Hugging Face models, demo Spaces and datasets implementing a paper.

## FAQ

### Is this server affiliated with Papers With Code?

No. The README describes it as an independent, unofficial integration, and the search tool is backed by Hugging Face Papers, the successor to Papers with Code.

### Do I need an API key?

No. Calls work anonymously with a daily cap. The README says a free Pipeworx key raises the cap to 200 calls a day.

### How do I find a paper's code?

Use the implementation lookup tool with the paper's arXiv id to get the linked GitHub repository and related Hugging Face resources.

### Is Paperswithcode free?

Paperswithcode has a free plan, with paid plans for more usage or features. Paid plans start at $49 a month.

### How do I add Paperswithcode to Claude Code?

Run this command in your terminal: claude mcp add --transport http paperswithcode https://gateway.pipeworx.io/paperswithcode/mcp

### What are the best alternatives to Paperswithcode?

The closest alternatives to Paperswithcode are Trending AI Papers — buy per-query in-session (hfpaperwatch), Semanticscholar, Figshare, WritersLogic research agents and Dataverse Harvard.

## Where this comes from

- Description: written from the project's README, the project's website and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [Trending AI Papers — buy per-query in-session (hfpaperwatch)](https://ai-powered.com/mcp/trending-ai-papers-buy-per-query-in-session-hfpaperwatch): Trending AI Papers — buy per-query in-session (hfpaperwatch) is a paid MCP server for academic research.
- [Semanticscholar](https://ai-powered.com/mcp/semanticscholar-2): Semanticscholar is a freemium MCP server for academic research.
- [Figshare](https://ai-powered.com/mcp/figshare): Figshare is a freemium MCP server for academic research.
- [WritersLogic research agents](https://ai-powered.com/mcp/writerslogic-research-agents): WritersLogic research agents is an MCP server for academic research.
- [Dataverse Harvard](https://ai-powered.com/mcp/dataverse-harvard): Dataverse Harvard is a freemium MCP server for academic research.
- [NCBI PubMed MCP by usefulapi](https://ai-powered.com/mcp/ncbi-pubmed-mcp-by-usefulapi): NCBI PubMed MCP by usefulapi is a freemium MCP server for health and science.
- [Europepmc](https://ai-powered.com/mcp/europepmc): Europepmc is a freemium MCP server for academic research.

---
Source: https://ai-powered.com/mcp/paperswithcode
