Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/GtJerry111/paperwithcode-hf-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/gtjerry111/paperwithcode-hf-mcp/paperwithcode-mcp)<a href="https://agentmods.dev/mcp/gtjerry111/paperwithcode-hf-mcp/paperwithcode-mcp"><img src="https://agentmods.dev/badge/mcp/gtjerry111/paperwithcode-hf-mcp/paperwithcode-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/gtjerry111/paperwithcode-hf-mcp/paperwithcode-mcp"><img src="https://agentmods.dev/badge/mcp/gtjerry111/paperwithcode-hf-mcp/paperwithcode-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
paperwithcode-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
86% identical to cort-mcp — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{ "paperwithcode-mcp": { "command": "uvx", "args": [ "paperwithcode-mcp" ] } }
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 8 lines scan A e09027cb003f
paperwithcode-mcp is an MCP server published in the GitHub repository GtJerry111/paperwithcode-hf-mcp (1 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. It is 86% identical to cort-mcp, differing in 4 lines, and is treated as a copy.
Other mcp servers, from other repositories
zero-to-ai-rag
MCP server "zero-to-ai-rag" as configured in PavanMudigonda/zero-to-ai. Runs scripts/rag_mcp_server.py with python.
huggingface
Hugging Face Hub MCP — models, datasets, spaces. Remote server at gateway.pipeworx.io.
volcengine
ByteDance Volcano Engine (Doubao) MCP server. Runs locally from the volcengine-mcp npm package.
watsonx
IBM watsonx.ai MCP server for Claude integration. Runs locally from the watsonx-mcp-server npm package.
mle-kit-mcp
MCP server that provides different tools for MLE. Runs locally from the mle-kit-mcp Python package.
cocktails-rag-mcp-server
MCP server "cocktails-rag-mcp-server" as configured in 00200200/cocktails-rag-mcp. Runs locally from the cocktails-rag-mcp-server Python package.