Papers
Scholarly paper search with real citations for AI assistants, over MCP.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"papers": {
"url": "https://papers-mcp.vercel.app/mcp"
}
}
}远程端点
https://papers-mcp.vercel.app/mcpstreamable-http它能做什么
工具清单
工具（4）
🟢search_papers(query, year_from, year_to, field, open_access, ...)
Search peer-reviewed and preprint records by question or keywords. Filters: year_from, year_to, field, open_access, and source (openalex, semantic_scholar, pubmed, crossref, arxiv, or all). Returns only works those APIs returned, each with a source link and an identifier. An empty list means the APIs returned nothing. Do not invent papers to fill a gap.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 2,
"maxLength": 400,
"description": "Question or keywords"
},
"year_from": {
"type": "integer",
"minimum": 1800,
"maximum": 2100
},
"year_to": {
"type": "integer",
"minimum": 1800,
"maximum": 2100
},
"field": {
"type": "string",
"minLength": 2,
"maxLength": 80,
"description": "Subject area, such as Medicine or Computer Science"
},
"open_access": {
"type": "boolean"
},
"source": {
"type": "string",
"enum": [
"openalex",
"semantic_scholar",
"pubmed",
"crossref",
"arxiv",
"all"
],
"description": "Index to search. Defaults to all, which mixes sources."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 20,
"description": "Maximum papers to return. Defaults to 8."
}
},
"required": [
"query"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"data": {}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_paper(identifier)
Fetch one paper's title, authors, year, venue, and abstract by DOI, PMID, arXiv id, or OpenAlex work id. Metadata comes from the API that resolved the identifier. If no source returns a record, say so. Do not guess the abstract.
输入模式
{
"type": "object",
"properties": {
"identifier": {
"type": "string",
"minLength": 2,
"maxLength": 300,
"description": "DOI, PMID, arXiv id, or OpenAlex work id"
}
},
"required": [
"identifier"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"data": {}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢find_related_papers(identifier, relation, limit)
List papers that cite a work (relation cited_by) or papers that work cites (relation references). Every row is an API hit. An empty list means the API returned none, not that none exist.
输入模式
{
"type": "object",
"properties": {
"identifier": {
"type": "string",
"minLength": 2,
"maxLength": 300
},
"relation": {
"type": "string",
"enum": [
"cited_by",
"references"
]
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 20
}
},
"required": [
"identifier",
"relation"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"data": {}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢format_citation(identifier, style)
Format a real paper in APA, MLA, Chicago author-date, or BibTeX using metadata fetched for the identifier. Titles are kept as the source provided them. Author particles may need a human check because display names are split mechanically. If the paper cannot be resolved, do not hand-write a citation.
输入模式
{
"type": "object",
"properties": {
"identifier": {
"type": "string",
"minLength": 2,
"maxLength": 300
},
"style": {
"type": "string",
"enum": [
"apa",
"mla",
"chicago",
"bibtex"
]
}
},
"required": [
"identifier",
"style"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"data": {}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}社区
证据