Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
An MCP server for analyzing PCAP files.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"mcpcap": {
"command": "uvx",
"args": [
"mcpcap"
]
}
}
}在终端中运行这条命令
claude mcp add mcpcap -- uvx mcpcap粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"mcpcap": {
"command": "uvx",
"args": [
"mcpcap"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"mcpcap": {
"type": "stdio",
"command": "uvx",
"args": [
"mcpcap"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过域名 mcpcap.ai 验证(注册中心会核实域名所有权)
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.10.0)于37天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。
同一分类中有:Spec Driven Development, Remote Desktop Commander, LickityClick
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Create, edit and track LickityClick short links, campaigns and click stats from your AI assistant.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
A modular Python MCP (Model Context Protocol) server for analyzing PCAP files. mcpcap exposes protocol-specific analysis tools that accept a local file path or remote HTTP URL at call time, so the server stays stateless and works cleanly with MCP clients.
mcpcap uses a modular architecture to analyze different network protocols found in PCAP files. Each module provides specialized analysis tools that can be called independently with any PCAP file, making it perfect for integration with Claude Desktop and other MCP clients.
mcpcap requires Python 3.10 or greater.
pip install mcpcap
uv add mcpcap
uvx mcpcap
Build the image from the repository root:
docker build -t mcpcap .
Run it over HTTP for MCP clients that connect to a network endpoint:
docker run --rm \
-p 127.0.0.1:8080:8080 \ -v "$(pwd)/examples:/pcaps:ro" \ mcpcap --transport http --host 0.0.0.0 --port 8080 --allow-unauthenticated-http
Run it over stdio for clients that can spawn docker run directly:
docker run --rm -i \
-v "$(pwd)/examples:/pcaps:ro" \ mcpcap
When you mount local captures into the container, use the container path in tool calls:
analyze_dns_packets("/pcaps/dns.pcap")
Remote http:// and https:// PCAP URLs work without a volume mount because mcpcap downloads them inside the container at call time.
For the default HTTP workflow, start the bundled Compose service:
docker compose up
This pulls ghcr.io/mcpcap/mcpcap:latest, publishes http://127.0.0.1:8080/mcp only on host loopback, and mounts ./examples into the container as /pcaps.
analyze_dns_packets("/pcaps/dns.pcap")
To analyze your own captures, change the volume in docker-compose.yml from ./examples:/pcaps:ro to your local capture directory.
For local development against the checked-out source instead of GHCR:
docker compose -f docker-compose.yml -f docker-compose.dev.yml up --build
Start mcpcap as a stateless MCP server:
# Default stdio transport for Claude Desktop and similar clients
mcpcap
mcpcap --modules dns,tcp
mcpcap --max-packets 1000
mcpcap --transport http --host 127.0.0.1 --port 8080
Use stdio transport for local MCP clients like Claude Desktop:
{
"mcpServers": { "mcpcap": { "command": "mcpcap", "args": [] } } }
Use HTTP transport when your MCP client expects a network endpoint:
mcpcap --transport http --host 127.0.0.1 --port 8080
Point your HTTP-capable MCP client at:
http://127.0.0.1:8080/mcp
Docker users can publish the same endpoint with:
docker run --rm \
-p 127.0.0.1:8080:8080 \ -v "/path/to/captures:/pcaps:ro" \ mcpcap --transport http --host 0.0.0.0 --port 8080 --allow-unauthenticated-http
Or with Compose:
docker compose up
HTTP binds on non-loopback interfaces require the MCPCAP_AUTH_TOKEN environment secret. Set a strong random secret through your secret manager or enter it without recording it in shell history:
read -rs -p "HTTP bearer token: " MCPCAP_AUTH_TOKEN
export MCPCAP_AUTH_TOKEN mcpcap --transport http --host 0.0.0.0 --port 8080
Clients must send Authorization: Bearer on every request. Use a TLS reverse proxy and an HTTPS URL for remote clients. A configured token also protects loopback endpoints; stdio is unaffected. The Docker examples use --allow-unauthenticated-http to bind inside the container while publishing only to host loopback. Keep that loopback mapping and use a trusted local Docker network; other containers on the same network can reach the service. Compose forwards MCPCAP_AUTH_TOKEN when set, so you can also secure the local container endpoint. See the HTTP integration guide for details.
Use the analysis tools with any PCAP file by providing the file path or URL when you call the tool:
DNS Analysis:
analyze_dns_packets("/path/to/dns.pcap")
analyze_dns_packets("https://example.com/remote.pcap")
DHCP Analysis:
analyze_dhcp_packets("/path/to/dhcp.pcap")
analyze_dhcp_packets("https://example.com/dhcp-capture.pcap")
ICMP Analysis:
analyze_icmp_packets("/path/to/icmp.pcap")
analyze_icmp_packets("https://example.com/ping-capture.pcap")
TCP Connection Analysis:
analyze_tcp_connections("/path/to/capture.pcap")
analyze_tcp_connections("/path/to/capture.pcap", server_ip="192.168.1.1", server_port=80)
TCP Pattern Analysis:
analyze_tcp_anomalies("/path/to/capture.pcap", server_ip="10.0.0.1")
TCP Retransmission Analysis:
analyze_tcp_retransmissions("/path/to/capture.pcap")
Traffic Flow Analysis:
analyze_traffic_flow("/path/to/capture.pcap", server_ip="192.168.1.100")
SIP Analysis:
analyze_sip_packets("/path/to/voip-signaling.pcap")
analyze_sip_packets("https://example.com/sip-call-flow.pcap")
CapInfos Analysis:
analyze_capinfos("/path/to/any.pcap")
analyze_capinfos("https://example.com/capture.pcap")
If you are using Docker with a bind mount, pass the in-container path instead of the host path:
analyze_capinfos("/pcaps/dns.pcap")
mcpcap provides specialized analysis prompts to guide LLM analysis:
# Load specific modules
mcpcap --modules dns # DNS analysis only mcpcap --modules tcp # TCP analysis only mcpcap --modules dhcp # DHCP analysis only mcpcap --modules icmp # ICMP analysis only mcpcap --modules sip # SIP analysis only mcpcap --modules dns,tcp # DNS and TCP analysis mcpcap --modules dns,dhcp,icmp,tcp,sip,capinfos # All modules (default)
# Limit packet analysis for large files
mcpcap --max-packets 1000
# Default stdio transport
mcpcap
mcpcap --transport http
mcpcap --transport http --host 0.0.0.0 --port 9000
mcpcap --modu只显示了开头部分;其余内容请在仓库中阅读