Summary
Connects Claude to the Papers With Code database of machine learning research papers and their associated code repositories. The source doesn't list specific tools, but it's hosted through Pipeworx's gateway infrastructure which handles 250+ data sources with a natural language query interface via ask_pipeworx. You can run it standalone or as part of the full Pipeworx gateway. Useful when you need to search ML literature, find implementations of specific techniques, or explore what code exists for recent papers. The natural language wrapper means you can ask questions instead of wrestling with search parameters.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →mcp-paperswithcode
Papers (ML research) MCP.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
Tools
| Tool | Description |
|---|---|
search_papers | Search machine-learning / AI research papers (via Hugging Face Papers, the successor to Papers with Code). Returns arXiv id, title, authors, community upvotes, and a linked GitHub repo when available. Use for "papers on ", "recent ML research about X". |
trending_papers | Today's trending ML/AI papers (or a given day's), ranked by community upvotes, via Hugging Face Papers. Use for "what are the hot AI papers", "trending ML research", "top papers this week". |
get_paper | Get full detail for a paper by its arXiv id (e.g. "2312.00752"): title, authors, abstract, AI-generated summary and keywords, community upvotes, and counts of linked models / datasets / demo Spaces. |
get_repositories | Find IMPLEMENTATIONS of a paper (by arXiv id): the linked GitHub repository plus the most popular Hugging Face models, demo Spaces, and datasets that implement or reproduce it — the "papers with code" view. Use for "code/implementation for ", "models trained on ". |
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"paperswithcode": {
"url": "https://gateway.pipeworx.io/paperswithcode/mcp"
}
}
}
What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/paperswithcode/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Paperswithcode data" })
The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →