Keel
Network diagnostics — ping, traceroute, DNS lookup, port scanning, and connectivity testing via MCP.
README
Sounding
Network Diagnostics MCP Server
Probing what lies beneath the surface -- network diagnostics for AI tools.
What It Does
Sounding is a Model Context Protocol (MCP) server that gives AI assistants 14 network diagnostic tools. It handles the things you'd normally reach for ping, dig, nmap, or openssl to do -- but exposed as structured, validated MCP tool calls.
Tools
| Tool | Description | Key Parameters |
|---|---|---|
health |
Server version and status check | -- |
ping |
TCP connect ping (port 80) with latency stats | host, count (1--100), timeout |
traceroute |
Trace network route to a host | host, max_hops (1--64) |
dns_lookup |
Resolve DNS records (A, AAAA, MX, CNAME, TXT, NS) | domain, record_type, nameserver |
reverse_dns |
Reverse DNS lookup for an IP address | ip |
port_check |
Check if a single TCP port is open | host, port, timeout |
port_scan |
Scan common TCP ports (rate-limited, max 100) | host, ports |
check_ssl_cert |
Inspect SSL/TLS certificate details and expiry | host, port |
whois_lookup |
WHOIS domain registration lookup | domain |
http_check |
HTTP request with status, timing, headers, size | url |
subnet_scan |
Discover live hosts on a local subnet (RFC 1918 only) | subnet (CIDR, max /20) |
get_public_ip |
Get the machine's public IP address | -- |
speed_test |
Measure download speed (Mbps) and latency | -- |
dns_propagation |
Check DNS propagation across public resolvers | domain, record_type |
Installation
From PyPI:
pip install sounding-mcp
Or isolated with pipx:
pipx install sounding-mcp
Usage
Run the server directly (stdio transport):
sounding
Claude Code
Register as a local MCP server:
claude mcp add sounding -- sounding
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"sounding": {
"command": "sounding",
"args": []
}
}
}
If installed in a virtual environment, use the full path to the binary:
{
"mcpServers": {
"sounding": {
"command": "/path/to/.venv/bin/sounding",
"args": []
}
}
}
Security
Sounding is designed to be safe for AI-driven use:
- SSRF protection --
http_checkresolves hostnames and blocks requests to internal, private, loopback, and link-local IP addresses (including IPv4-mapped IPv6). Cloud metadata endpoints (169.254.x.x) are blocked. - Input validation -- All inputs pass through validators that reject shell metacharacters, malformed hostnames, and invalid ports before reaching any network call or subprocess.
- Rate limiting --
port_scanenforces a minimum 1-second interval between scans to prevent abuse. - Subnet restriction --
subnet_scanonly allows RFC 1918 private subnets and caps at /20 (4096 addresses) with concurrency limiting. - No shell injection -- Subprocess calls (
traceroute,whois) useexec-style invocation, never shell interpolation.
Development
git clone https://github.com/seayniclabs/sounding.git
cd sounding
python -m venv .venv
source .venv/bin/activate
pip install -e ".[test]"
python -m pytest tests/ -q
License
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。