NebulaFinger MCP

项目关系说明：本MCP模块是NebulaFinger指纹识别工具的AI代理接口实现。完整的独立MCP实现可在MCP-NebulaFinger找到。该接口使大型语言模型能够直接调用NebulaFinger进行Web和服务指纹识别。
- Python 3.8+已安装
- NebulaFinger.exe工具已构建或下载
- FastMCP库已安装

NebulaFinger/ ├── NebulaFinger.exe # 主程序 ├── configs/ # 配置目录 │ ├── web_fingerprint_v4.json │ ├── service_fingerprint_v4.json │ ├── fingerprint_weights.json │ └── tcp_ports.json ├── MCP/ # MCP 服务目录 │ └── mcp_server.py # MCP 服务端脚本 └── README.md

{ "mcpServers": { "nebulafinger_mcp": { "isActive": true, "name": "nebulafinger_mcp", "type": "stdio", "command": "python", "args": [ "D:\\NebulaFinger\\MCP\\mcp_server.py" ], "env": { "NEBULAFINGER_PATH": "D:\\NebulaFinger" } } } }

- 请将路径替换为你的实际的绝对路径
- NEBULAFINGER_PATH环境变量指向 NebulaFinger 工具的根目录

参数： - target: 要扫描的目标 (例如: example.com 或 http://example.com) - mode: 扫描模式 ("web", "service", "all")，默认 "web" - concurrent: 并发数，默认 5 - output_html: 是否生成HTML报告，默认 False - silent: 静默模式，默认 False - no_favicon: 禁用Favicon检测，默认 False - bp_stat: 只输出有指纹匹配的结果，默认 False

参数： - targets: 要扫描的目标列表 (字符串数组) - 其他参数与 scan_target 相同

参数： - file_path: 包含目标列表的文件路径 - 其他参数与 scan_target 相同

在 MCP 客户端中（以Cherry Studio+qwen-plus为例），你可以这样使用：

（请使用 NebulaFinger） 扫描 www.baidu.com 的 web 指纹

使用 NebulaFinger 扫描以下网站的指纹www.baidu.com、www.github.com

读取文件D:\学习计划进度\GO\NebulaFinger\url_small.txt，并依次进行指纹识别，并生成结果html

- 确保NEBULAFINGER_PATH环境变量正确设置
- 或者在命令行参数中指定正确的路径
- 检查文件是否存在且有执行权限

- 确保 configs 目录存在
- 检查指纹库文件是否完整
- 验证文件路径是否正确（使用绝对路径）

- 确保 Python 进程有权限访问 NebulaFinger.exe
- 检查文件和目录的读写权限
- 更新指纹库：直接替换 configs 目录下的指纹库文件
- 更新工具：替换 NebulaFinger.exe 文件
- 更新 MCP 服务：修改 mcp_server.py 文件后重启 MCP 客户端

Chia Health MCP Server — Patient workflow integration for a licensed US telehealth platform. Browse GLP-1 medications (semaglutide, tirzepatide), peptide therapies (sermorelin, NAD+, glutathione), and longevity treatments. Check eligibility, complete intake, sign consents, and manage treatment plans. 30 tools, HIPAA-compliant. All prescriptions evaluated by licensed US healthcare providers and delivered from FDA-regulated pharmacies across 50 states + DC.

Broker + MCP server for last-bidder-wins games on Solana — agents register, auto-fund a Privy wallet, and bid via streamable HTTP

AI-powered no-code app builder with 17 MCP tools — create projects, generate pages from natural language, AI text/image generation (GPT, Claude, Gemini, 14+ models), page CRUD, workflow execution, publish & version control. SSE transport, API key auth.

An mcp server for your food ordering needs.

Agent-to-Agent handoff certification for multi-agent systems — validates context preservation, verifies agent capabilities before handoff, logs transfer chains, and ensures no data loss in agent orchestration.

Unified MCP & skill management gateway with progressive disclosure. Manages multiple MCP servers as Agent Apps, loading tool schemas on demand for 99% context token savings. Shared across Claude Code, Codex, OpenCode and more.

A collection of Model Context Protocol (MCP) servers for various tasks and integrations, supporting both Python and Node.js environments.

Open-souSecurely feeds real security refreshed rules into Cursor, Claude Code, and Windsurf — zero config, no API key.

Health intelligence MCP — access biomarkers, biological age, and personalized longevity action plans from your Aniva profile.

Real-time stock heatmaps and investment tools delivered as interactive React components.