PapersFlow

PapersFlow

Turn any AI agent into an academic researcher that can search, read, cite, and write full literature reviews autonomously.

Category
访问服务器

README

papersflow-mcp

papersflow-mcp is PapersFlow's production / GA hosted MCP server for literature search, citation verification, related-paper discovery, and authenticated research workflows across Claude, Codex, Gemini, ChatGPT-style MCP apps, and other MCP clients.

<a href="https://glama.ai/mcp/servers/papersflow-ai/papers-flow"> <img width="380" height="200" src="https://glama.ai/mcp/servers/papersflow-ai/papers-flow/badge" alt="PapersFlow MCP server" /> </a>

Production Endpoint

  • MCP URL: https://doxa.papersflow.ai/mcp
  • OAuth protected resource metadata: https://doxa.papersflow.ai/.well-known/oauth-protected-resource
  • OAuth authorization server metadata: https://doxa.papersflow.ai/.well-known/oauth-authorization-server
  • Dynamic client registration: https://doxa.papersflow.ai/oauth/register

Public Tool Surface

  • search
  • fetch
  • verify_citation
  • search_literature
  • find_related_papers
  • get_citation_graph
  • get_paper_neighbors
  • expand_citation_graph

Authenticated and paid tools are available through PapersFlow account access and plan entitlements.

Documentation

Gemini CLI Extension

This repository also includes a root gemini-extension.json so Gemini CLI can install it as an extension wrapper around the hosted MCP server.

Official Gemini CLI flow supported by the docs:

gemini extensions install https://github.com/papersflow-ai/papersflow-mcp

The extension manifest lives at the repository root and points Gemini CLI at the hosted MCP endpoint using Gemini's remote MCP config shape.

If Gemini shows:

papersflow-mcp (from papersflow-mcp) - Disconnected (OAuth not authenticated)

that is expected until OAuth is completed inside Gemini:

/mcp auth papersflow-mcp
/mcp refresh
/mcp list

gemini extensions install installs the extension package. It does not complete OAuth during install. The browser opens when Gemini starts the remote MCP auth flow, typically via /mcp auth papersflow-mcp or the first auth-required connection attempt.

Gemini CLI references:

  • https://geminicli.com/docs/extensions/releasing/
  • https://geminicli.com/docs/extensions/reference/
  • https://geminicli.com/docs/extensions/writing-extensions/

Client Setup

Cline (VS Code)

Add PapersFlow as a remote MCP server in your Cline MCP settings:

{
  "mcpServers": {
    "papersflow": {
      "url": "https://doxa.papersflow.ai/mcp",
      "transportType": "streamable-http"
    }
  }
}

On first use, Cline will open a browser window for OAuth sign-in to your PapersFlow account. Public tools (literature search, citations, paper discovery) work immediately; authenticated tools require a PapersFlow plan.

Other Clients

Supported client paths today:

  • Codex
  • Claude Code
  • Gemini CLI
  • ChatGPT-style hosted MCP apps

The setup guide includes both command-style and config-style snippets where supported.

Support And Policies

  • Website: https://papersflow.ai
  • Privacy: https://papersflow.ai/privacy
  • Terms: https://papersflow.ai/terms
  • Support: https://papersflow.ai/contact
  • Support email: developer@papersflow.ai

Notes

  • This repository is the public documentation and submission surface for the hosted MCP service.
  • The production service is operated by PapersFlow and backed by the main PapersFlow platform.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选