
crypto-whitepapers-mcp
An MCP server serving as a structured knowledge base of crypto whitepapers for AI agents to access, analyze, and learn from.
README
Crypto Whitepapers MCP Server
An MCP server serving as a structured knowledge base of crypto whitepapers for AI agents to access, analyze, and learn from.
Features
- Search Whitepapers: Use DuckDuckGo to find whitepaper PDFs for cryptocurrency projects.
- Load Whitepapers: Download and index whitepaper PDFs into the knowledge base.
- Query Knowledge Base: Query whitepaper content with optional project filtering.
- List Projects: View all projects available in the knowledge base.
- Claude Desktop Integration: Access tools and prompts via MCP in Claude Desktop.
Prerequisites
- Python 3.10+
- uv for dependency management and running
- Internet access.
- Claude Desktop for MCP integration (optional)
Setup
-
Clone the Repository:
git clone https://github.com/kukapay/crypto-whitepapers-mcp.git cd crypto-whitepapers-mcp
-
Install Dependencies with uv:
uv sync
-
Integrate with Claude Desktop (Optional):
- Edit the Claude Desktop configuration file:
- MacOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
%APPDATA%\Claude\claude_desktop_config.json
- MacOS:
- Add the following configuration:
Replace{ "mcpServers": { "crypto-whitepapers": { "command": "uv", "args": [ "--directory", "/absolute/path/to/crypto-whitepapers-mcp" "run", "crypto-whitepapers-mcp" ] } } }
/absolute/path/to/crypto-whitepapers-mcp
with the absolute path to the repository. - Restart Claude Desktop and verify the server is loaded (look for the hammer icon in the input box).
- Edit the Claude Desktop configuration file:
Usage
Tools
The following tools are available via the MCP server:
-
list_available_projects()
: Lists all projects in the knowledge base (derived from PDF filenames).- Example:
list_available_projects()
- Returns: JSON list of project names.
- Example:
-
search_whitepaper(project_name: str)
: Searches for a project's whitepaper PDF using DuckDuckGo.- Example:
search_whitepaper("bitcoin")
- Returns: JSON list of up to 5 results with title, URL, and snippet.
- Example:
-
load_whitepaper(project_name: str, url: str)
: Downloads a whitepaper PDF from a URL and loads it into the knowledge base.- Example:
load_whitepaper("bitcoin", "https://bitcoin.org/bitcoin.pdf")
- Returns: Success or error message.
- Example:
-
ask_whitepapers(query: str, project_name: str = None)
: Searches the knowledge base for a query, optionally filtered by project.- Example:
ask_whitepapers("blockchain technology", "bitcoin")
- Returns: Up to 5 matching text snippets.
- Example:
Prompts
analyze_tokenomics(project_name: str)
: Analyzes tokenomics (distribution, supply, incentives) in a project's whitepaper using theask_whitepapers
tool.- Example: In Claude Desktop, run "Analyze the tokenomics of Ethereum."
Examples
- List available projects:
List all available projects.
- Search for a whitepaper:
Search for the Bitcoin whitepaper PDF.
- Load a whitepaper:
Load the Bitcoin whitepaper from https://bitcoin.org/bitcoin.pdf.
- Query the knowledge base:
Ask the knowledge base about blockchain technology in the Bitcoin whitepaper.
License
This project is licensed under the MIT License. See the LICENSE file for details.
推荐服务器

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。
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。
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。
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。

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。
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。
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。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。