fiddler-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@fiddler-mcp analyze capture.saz and list sessions with 4xx errors"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
fiddler-mcp
一个 MCP (Model Context Protocol) 服务,用于分析 Telerik Fiddler 抓包产生的 SAZ 会话存档。
把 Fiddler 导出的 .saz 文件交给这个服务,即可让 AI 助手完成:
会话总览:方法 / 状态码 / 域名 / Content-Type 分布、流量体积、耗时分位数、4xx/5xx 错误样本
会话详情:任意会话的完整请求与响应(请求行/状态行、全部 headers、自动解压并解码的 body)
过滤与搜索:按 Host、方法、状态码、URL 关键词/正则、请求/响应正文关键词、大小、耗时组合过滤
性能分析:最慢请求 Top N、耗时分布(DNS / TCP 连接 / TLS / 总耗时)
安全审计:明文 HTTP 传输凭证、URL/正文中的密钥与 Token、Cookie 缺少 Secure/HttpOnly、敏感文件泄露、响应中的 PII(邮箱/手机号)等
工作原理
SAZ 是 ZIP 容器,内部结构(Fiddler Classic 5.x 及兼容版本):
sample.saz
├── raw/
│ ├── 1_c.txt 客户端请求(请求行 + headers + body)
│ ├── 1_s.txt 服务端响应(状态行 + headers + body)
│ ├── 1_m.xml 会话元数据(SessionTimers 计时 / SessionFlags 进程名)
│ └── 1_w.txt 可选:WebSocket 消息
└── _index.htm 可选:会话索引(用于提取 Comments)body 按 wire 原始字节存储,可能带 Content-Encoding: gzip/deflate/br,服务在展示与搜索时自动解压。
Related MCP server: Charles MCP Server
安装
cd E:\McpService\fiddler-mcp
python -m venv .venv
.venv\Scripts\pip install -e ".[dev]"国内网络可加清华镜像:
.venv\Scripts\pip install -i https://pypi.tuna.tsinghua.edu.cn/simple -e ".[dev]"
依赖
mcp(官方 Python SDK),当前锁定mcp>=1.2,<2.0(2.0 重构了 FastMCP API,暂不兼容)。
在 Fiddler 中导出 SAZ
打开 Fiddler Classic,抓包完成后选中需要的会话
File → Export Sessions → All Sessions保存类型选择 SAZ Archives(文件名以
.saz结尾)
接入 MCP 客户端
Claude Desktop(claude_desktop_config.json)
{
"mcpServers": {
"fiddler-mcp": {
"command": "E:\\MCP\\Fiddler\\.venv\\Scripts\\python.exe",
"args": ["-m", "fiddler_mcp"],
"cwd": "E:\\MCP\\Fiddler"
}
}
}Cursor / 其他支持 stdio MCP 的工具
在 .mcp.json(项目级)或全局配置中加入:
{
"mcpServers": {
"fiddler-mcp": {
"command": "E:\\MCP\\Fiddler\\.venv\\Scripts\\python.exe",
"args": ["-m", "fiddler_mcp"]
}
}
}命令行冒烟测试
.venv\Scripts\python -c "import fiddler_mcp.server as s; print(s.mcp.list_tools())"提供的工具
工具 | 说明 |
| 解析并缓存 SAZ,返回概览(支持 |
| 分页列出会话摘要 |
| 单个会话完整详情 |
| 组合条件过滤/搜索(Host、方法、状态码、URL 关键词/正则、正文关键词、大小、耗时) |
| 聚合统计 |
| 最慢请求排名 |
| 安全审计,按 high/medium/low 分级输出 |
开发与测试
.venv\Scripts\python -m pytest测试通过合成 SAZ 夹具(覆盖 gzip body、UTF-8 BOM、中文 URL、空响应、WebSocket 标记、_index.htm 注释)验证解析与各分析功能。
已知限制
解析器面向 Fiddler Classic 现代版本(
raw/<N>_c.txt/_s.txt/_m.xml结构);极老版本的cXXXXcYYYY命名格式不支持_index.htm仅作 Comments 提取(尽力而为,失败不影响核心解析)会话计时来自
_m.xml的SessionTimers;SAZ 中不包含绝对时间戳(无法还原真实抓包时刻)安全扫描为启发式正则,可能存在误报/漏报,结论需人工复核
出于安全考虑,
list_sessions/filter_sessions/session_stats/slow_requests/security_scan的输出会对 URL 中敏感查询参数(token、password、secret、api_key 等)及 fragment 自动脱敏;get_session是唯一返回完整 URL 与 body 的工具(用于深入检查单条会话)防御性上限:单个 zip 条目 > 512MB 跳过、元数据条目 > 16MB 跳过、body 解压预览上限 64MB、
url_regex最长 200 字符
Available Tools
7 toolsfilter_sessionsA
Search/filter sessions by host, method, status, URL keyword or regex, body keywords, size and duration.
Args: saz_path: Path to the .saz file. host: Substring match on Host[:port]. method: HTTP method, e.g. GET/POST (case-insensitive). status: Exact status code. status_min / status_max: Status code range. url_keyword: Case-insensitive substring of the URL. url_regex: Regex (Python syntax, max 200 chars) matched against the URL. req_body_keyword: Substring search inside the decoded request body. resp_body_keyword: Substring search inside the decoded response body. min_size / max_size: Request+response body size range in bytes. min_ms / max_ms: Total duration range in milliseconds. only_errors: Only 4xx/5xx responses. only_redirects: Only 3xx responses. only_success: Only 2xx responses. with_response: True/False to require/forbid a response. websocket: True/False to require/forbid WebSocket messages. limit: Max sessions returned (1-1000).
Inputs: saz_path (required), host, limit, max_ms, +16 more.
get_sessionA
Full details of one session: request & response start lines, headers, bodies, timers, flags.
This is the only tool that returns the complete (unredacted) URL and bodies — intended for deep inspection of a specific session.
Args: saz_path: Path to the .saz file. index: Session number (1-based, as shown by list_sessions). include_body: Decode and show bodies (may be truncated). max_body_chars: Max chars of each decoded body to include.
Inputs: index (required), saz_path (required), include_body, max_body_chars.
list_sessionsA
List sessions (method, URL, status, duration, size, process...) with pagination.
Args: saz_path: Path to the .saz file (parsed on first use). limit: Max sessions to return (1-500). offset: Skip the first N sessions (pagination).
Inputs: saz_path (required), limit, offset.
open_archiveA
Parse a Fiddler .saz archive and return an overview. Archives are cached; use reload=true to re-read.
Args: saz_path: Path to the .saz file. reload: Re-parse the file even if already cached.
Inputs: saz_path (required), reload.
security_scanA
Scan traffic for security issues: cleartext credentials, secret tokens in URLs/bodies, cookie flags, sensitive files, PII leakage.
Args: saz_path: Path to the .saz file. max_findings: Cap on reported findings (1-2000).
Inputs: saz_path (required), max_findings.
session_statsB
Aggregate statistics: method/status/host distribution, traffic volume, duration percentiles, error samples.
Args: saz_path: Path to the .saz file.
Inputs: saz_path (required).
slow_requestsA
Rank sessions by total duration (Fiddler TOTAL = ClientDoneResponse - ClientBeginRequest).
Args: saz_path: Path to the .saz file. top_n: How many slowest sessions to return (1-100). min_ms: Only consider sessions slower than this threshold.
Inputs: saz_path (required), top_n, min_ms.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool has a clearly distinct purpose: opening the archive, listing sessions, inspecting a single session, filtering by criteria, computing statistics, ranking slow requests, and security scanning. Even the overlapping list/filter tools are differentiated by filtering vs. plain pagination, and slow_requests is a specific ranking view.
Most tools follow a verb_noun pattern (open_archive, list_sessions, get_session, filter_sessions), but session_stats, slow_requests, and security_scan use descriptive noun phrases rather than imperative verbs. All names are snake_case and readable, so the deviation is minor.
Seven tools is well-scoped for a Fiddler archive analysis server. Each tool earns its place, covering the full range of archive inspection and analysis without redundancy or bloat.
The toolset covers the complete analysis workflow: loading/parsing the archive, listing sessions, deep inspection, filtering/searching, aggregate statistics, performance ranking, and security scanning. Minor potential gaps like archive comparison or export are not core to the domain.
Maintenance
Related MCP Connectors
Website health, SEO, security-header, SSL and broken-link audits for AI agents.
Scan PDFs, Office docs, and RAG files for malware exploits, macros, CVEs, and AI prompt injection.
AI website audit: security, SEO, performance, UX and accessibility checks with actionable fixes.
Scan websites and code for security, performance and SEO issues from your AI assistant.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI to analyze real-time HTTP(S) traffic captured by ProxyPin, with tools to browse, search, and inspect requests and responses, as well as access saved history sessions.11 npm4MIT
- AlicenseAqualityDmaintenanceEnables AI agents to interact with Charles Proxy for HTTP traffic analysis, supporting incremental harvest, checkpoint timelines, and rich filtering tools.138MIT
- AlicenseAqualityBmaintenanceEnables AI assistants to securely investigate packet captures through Wireshark's tshark engine, with bounded tools for protocol inventory, TCP failure diagnosis, latency measurement, and threat hunting.12MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to locally parse and analyze HAR files through read-only MCP tools, including searching requests, discovering endpoints, tracing values, detecting auth and API patterns, comparing requests, and exporting redacted cURL commands.-