Paper Pilot
未认领Your AI's research copilot. Searches 6 academic databases, downloads real PDFs, reads them cover to cover, extracts evidence, renders figures. MCP server for Claude, Codex & any AI agent. Free & open source.
安装
uvx --from git+https://github.com/aytzey/paper-pilot paper-pilot demo "retrieval augmented generation"更多Search & Web服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
12 个工具中显示 12 个
文档中列出的工具 (12)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
deep_read_topic
Everything above + full-text extraction with evidence chunks
extract_local_pdf_text
Text extraction from any local PDF
find_similar_papers
Related work expansion from a seed paper
get_pdf_page_text
Exact text of specific PDF pages as JSON, for fine-grained lookups (no base64)
graph_topic
Render an interactive citation / relatedness graph (HTML) for a topic
healthcheck
Verify all connections are up
inspect_open_access_pdf
OA availability check and PDF preview
list_zotero_collections
List collections in your local or web Zotero library
read_pdf_document
Return a downloaded PDF's local path and resource link (embed base64 only on request)
render_pdf_pages
Render PDF pages as images the model can see (figures, tables, layout)
research_topic
Full pipeline: search, download, report, optional citation graph + Zotero sync
search_literature
Fine-grained multi-source academic search (6 databases)