paper-search-mcp
Related Servers
Alternatives to paper-search-mcp
No user-submitted related servers found.
Related Servers
- AlicenseBqualityDmaintenanceAn MCP server for searching and downloading academic papers from multiple sources including arXiv, PubMed, bioRxiv, and Sci-Hub, designed for seamless integration with large language models like Claude Desktop.572,161 PyPI2,611MIT
- AlicenseNot gradedqualityDmaintenanceA MCP server for searching and downloading academic papers from arXiv, PubMed, bioRxiv, and more. It integrates with LLMs like Claude Desktop for paper discovery.MIT
- AlicenseAqualityFmaintenanceA Model Context Protocol server that enables natural language interaction with arXiv.org, allowing users to search, retrieve metadata, download PDFs, and load scholarly articles into LLM context.539MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol (MCP) server that provides AI assistants with a seamless, programmatic interface to search and read academic papers from the open-access arXiv repository.2MIT
- AlicenseAqualityFmaintenanceEnables searching and accessing academic papers from 23+ sources (including arXiv, PubMed, Google Scholar) through the Model Context Protocol, with unified tools for search, download, and text extraction.413 npm2MIT
- AlicenseAqualityAmaintenanceMulti-source academic paper search, citation graph exploration, and PDF download as an MCP server, designed for LLM agents doing research.6156 PyPI3Apache 2.0
TDQS
Scored across 57 tools
Each tool is clearly distinguished by source (e.g., arxiv, biorxiv, crossref) and action (search_, download_, read_). There is no ambiguity even among similar sources because the prefix uniquely identifies the platform.
All tool names follow a uniform verb_noun pattern: action_source (e.g., search_arxiv, download_pubmed, read_semantic). The convention is strictly maintained across all 57 tools, making it predictable and easy to parse.
With 57 tools, the set is overly large for the server's purpose. Many sources have separate tools for search, download, and read even when download/read are not supported, resulting in redundant error-returning tools. A more concise design would combine variants or use fewer tools.
The surface covers a broad range of academic sources, offering search, download, and read for most. However, some sources (e.g., crossref, pubmed, ssrn) have non-functional download/read tools that merely return errors, which is a minor gap. The unified search_papers tool partially mitigates this.