io.github.laibniz由 GitHub 账号 laibniz 发布v0.2.1更新于 Oct 27, 2026
Multi-engine scholarly research server for search, traversal, full text, and reading lists.
多引擎学术研究服务器，让助手检索论文、遍历作者与参考文献、阅读摘要和全文，并导出阅读清单。
Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。
把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。
阅读 https://sourceweft.com/mcp/io.github.laibniz%2Fscholarfetch/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。把它添加到你客户端的 mcpServers 配置中。
{
"mcpServers": {
"scholarfetch": {
"type": "http",
"url": "https://laibniz-scholarfetch-web.hf.space/mcp/"
}
}
}ScholarFetch is a multi-engine academic research environment for:
It combines:
stdio, sse, streamable-http)The core idea is simple: start from keywords, DOI, or authors, traverse papers and references, inspect abstracts and full text, save what matters, then export a compact corpus for synthesis.
Console scripts:
scholarfetchscholarfetch-mcpscholarfetch-fastmcpAlternative:
ScholarFetch loads provider credentials server-side / client-side from environment.
Default env file:
.scholarfetch.envTypical variables:
Notes:
ELSEVIER_INSTTOKEN is optionalScholarFetch CLI is designed for research traversal.
Typical flow:
Example:
OPEN, ABSTRACT, TEXT, REFS, and AUTHORBackspace to go to parent nodeEsc to return to promptS to save a paper from paper lists or reference listsX to remove from the saved listAUTHOR action from a paper now lets you select:
ALL AUTHORSopenabstracttextrefsauthor/search <keywords|doi|person name>/author <name>/papers <author name|index> [filters]/doi <doi>/open <index>/abstract <doi|index>/article <doi|index>/refs <doi|index>/ref <index>/saved/export [format style path ...]/import [path]/pick [mode]/config/engines/helpUse with /papers:
year>=YYYY, year<=YYYY, year=YYYYhas:abstract, has:doi, has:pdf, has:fulltextvenue:<text>, title:<text>, doi:<text>Examples:
ScholarFetch supports four export modes from the saved paper set.
bib
citations
harvard, apa, or ieeeabstracts
fulltext
This makes ScholarFetch useful as a corpus builder for downstream synthesis agents.
ScholarFetch exposes the same research model through MCP.
Modes:
python3 scholarfetch_mcp.pypython3 scholarfetch_fastmcp.py --transport stdiopython3 scholarfetch_fastmcp.py --transport sse --host 127.0.0.1 --port 8000python3 scholarfetch_fastmcp.py --transport streamable-http --host 127.0.0.1 --port 8000 --http-path /mcpValidation:
Public demo endpoints:
io.github.laibniz/scholarfetchThe MCP server is designed for agent workflows, not only one-off calls.
An agent can:
This lets an agent build a focused research set inside one MCP session and then hand off an export artifact to another synthesis step.
See MCP_SERVER.md for the detailed tool model.
scholarfetch.py: CLI entrypointscholarfetch_cli.py: core CLI + retrieval logicscholarfetch_mcp.py: classic MCP serverscholarfetch_fastmcp.py: FastMCP serverMCP_SERVER.md: MCP usage guideAGENTS.md: agent-facing workflow guideSKILL.md: structured research skill guideSKILLS.md: index for agent-facing skill docsCONTRIBUTING.md: contributor notesIf you are running ScholarFetch from an MCP-compatible system, read:
These documents explain how to use ScholarFetch as a literature-research environment rather than as a flat search API.
See CONTRIBUTING.md.
See SECURITY.md.
MIT License. See LICENSE.
来源：README.md，提交 103fcd5
Start a research traversal from keywords, a DOI, or a person name. Returns deduplicated paper records that you can inspect, save, expand through references, or use as seeds for author exploration. If you pass `engines`, use a comma-separated subset of: elsevier, openalex, crossref, arxiv, europepmc, springer, semanticscholar.
limitquery必填enginesEnrich one known DOI with metadata, reading links, and full-text availability signals. If you pass `engines`, use a comma-separated subset of: elsevier, openalex, crossref, arxiv, europepmc, springer, semanticscholar.
doi必填enginesDisambiguate a human author name into ranked identity candidates. Use this before `scholarfetch_author_papers` when the name is ambiguous and you need a stable `candidate_index`. If you pass `engines`, it must include `openalex`.
name必填limitenginesExpand one author into a deduplicated paper list. This is the main author->paper traversal tool and supports research filters. Use `author_id` when you already know the exact author, or `author_name` plus `candidate_index` after `scholarfetch_author_candidates`. Supported comma-separated `filters`: year>=YYYY, year<=YYYY, year=YYYY, has:abstract, has:doi, has:pdf, venue:<text>, title:<text>, doi:<text>. If you pass `engines`, it must include `openalex`.
limitenginesfiltersauthor_idauthor_namecandidate_indexRead the best abstract available for a paper. Use with a DOI or with author_name + candidate_index + paper_index after author_papers. If you pass `engines`, use a comma-separated subset of: elsevier, openalex, crossref, arxiv, europepmc, springer, semanticscholar.
doienginesauthor_namepaper_indexcandidate_indexRead full paper text when machine-readable content is recoverable. Use with a DOI or with author_name + candidate_index + paper_index. Uses Elsevier first, then open-access fallbacks such as Springer OA, Europe PMC, arXiv PDF, and generic PDF URLs when text is recoverable. If you pass `engines`, use a comma-separated subset of: elsevier, openalex, crossref, arxiv, europepmc, springer, semanticscholar.
doienginesauthor_namepaper_indexcandidate_indexExpand a paper into its references. Use with a DOI or with author_name + candidate_index + paper_index. This is the main edge-expansion tool for traversing the literature graph. If you pass `engines`, use a comma-separated subset of: elsevier, openalex, crossref, arxiv, europepmc, springer, semanticscholar.
doienginesauthor_namepaper_indexcandidate_indexAdd one paper to a named in-memory reading list on the MCP server. Best input is paper_json copied from another ScholarFetch tool result, but DOI, query+result_index, or author_name+candidate_index+paper_index also work. Reuse the same collection name across calls to keep one research session together.
doiqueryenginescollectionpaper_jsonauthor_namepaper_indexresult_indexcandidate_indexList all papers currently saved in a named in-memory reading list. Use this to inspect the working set before exporting or removing items.
collectionRemove one paper from a named in-memory reading list by DOI or exact title.
doititlecollectionClear all papers from a named in-memory reading list. Useful when restarting a research branch.
collectionExport the current reading list as citations, abstracts, BibTeX, or an aggregated full-text corpus. Valid `format` values: citations, abstracts, bib, fulltext. Valid `style` values when `format=citations`: harvard, apa, ieee. Use `include_references=true` with `format=fulltext` when you want a richer downstream synthesis corpus.
styleformatenginescollectioninclude_references已满足适用检查项的 100%
该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。
git clone https://github.com/laibniz/scholarfetch.gitcd scholarfetchpython3 -m venv .venvsource .venv/bin/activatepip install -e .scholarfetchpython3 scholarfetch.pyELSEVIER_API_KEY=...ELSEVIER_INSTTOKEN=...SPRINGER_META_API_KEY=...SPRINGER_OPENACCESS_API_KEY=.../search graph neural networks/author Albert Einstein/papers 1 has:abstract/article 1/refs 1/saved/export fulltext dummy corpus.txt/papers 1 year>=2020 has:abstract/papers 1 has:fulltext/papers andrea de mauro venue:marketingpython3 scholarfetch_mcp.py --self-testpython3 scholarfetch_fastmcp.py --self-test