Skip to main content
Glama

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

  1. 打开 Fiddler Classic,抓包完成后选中需要的会话

  2. File → Export Sessions → All Sessions

  3. 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

open_archive(saz_path)

解析并缓存 SAZ,返回概览(支持 reload 强制重读)

list_sessions(saz_path, limit, offset)

分页列出会话摘要

get_session(saz_path, index, include_body, max_body_chars)

单个会话完整详情

filter_sessions(...)

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)

session_stats(saz_path)

聚合统计

slow_requests(saz_path, top_n, min_ms)

最慢请求排名

security_scan(saz_path, max_findings)

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 tools
filter_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

    A4.1/5.0

    Scored across 7 tools

    Disambiguation5/5

    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.

    Naming Consistency4/5

    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.

    Tool Count5/5

    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.

    Completeness5/5

    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

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables 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 npm
      4
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables 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.
      12
      MIT
    • F
      license
      Not graded
      quality
      C
      maintenance
      Enables 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.
      -