Har Forensics Mcp

io.github.aryanspvPublished by GitHub account aryanspvv0.3.2Updated Oct 24, 2026

Tells you what leaked in a .har capture, who's on the page, and what to strip. No network calls.

Overview

AI-generated overview

Local MCP server that audits .har browser captures offline, reporting leaked credentials, third parties and what to strip before sharing.

What you can do
  • Locate .har captures on disk and triage a chosen file with a verdict per check
  • List findings worst-first by severity, score third-party vendors and trace who loaded whom
  • Explain performance: slowest requests, handshake cost per origin, uncompressed assets, redirect loss
  • Query requests with filters and inspect a single entry's headers, cookies, body and timings
  • Turn a request into a runnable cURL or fetch snippet with credentials masked, and diff two captures
  • Write a redacted .redacted.har copy and produce a redacted markdown brief
When to use it
Useful when you have a HAR file from browser dev tools and need to know what secrets or personal data it exposes, which third parties are involved, or why a page was slow, before attaching the capture to a ticket or chat.
Requirements
Runs as a local stdio process via npx (npm package har-forensics-mcp); Node 20 or newer. No API key, account or network access needed. Register it in your editor's MCP config (Claude Code, Cursor, Windsurf, Zed, VS Code Copilot) and restart the editor.
Before you install
HAR captures contain live session cookies, Authorization headers and sometimes card numbers; the server reads them locally and makes no network calls, but anything you paste from its output into a chat leaves your machine. sanitize_har writes a new file and refuses to overwrite existing targets or the original. Files above roughly 512 MB are rejected.

Installation

In SourceWeft

  1. Open Har Forensics Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

har-forensics-mcp

Audit a .har capture from inside your editor. Other HAR tools show you a list of requests. This one answers the question you opened the file for: what leaked, who's on the page, and what to strip before you send it anywhere.

Reads a file from local disk, computes, writes to stdout. It makes no network calls, which is the point: a real capture holds live session cookies, Authorization headers, and sometimes card numbers.

Works with anything that speaks MCP over stdio — Cursor, Claude Code, Windsurf, Zed, VS Code Copilot.

Setup

Claude Code:

bash
claude mcp add --scope user har-forensics -- npx -y har-forensics-mcp

--scope user registers it for every directory. Without it the server is scoped to whichever directory you ran the command in — which still reports success, and then the tools are silently absent everywhere else.

Cursor — .cursor/mcp.json in the project, or ~/.cursor/mcp.json globally:

json
{  "mcpServers": {    "har-forensics": {      "command": "npx",      "args": ["-y", "har-forensics-mcp"]    }  }}

Windsurf / Zed / VS Code Copilot take the same command + args shape in their own MCP config files.

Restart the editor, then point a tool at a capture:

Run analyze_har on ~/Downloads/checkout.har

Requires Node 20+. Nothing else — no clone, no build, no API key, no account.

Tools

ToolAnswers
find_captures"Where are my .har files?" — scans Downloads, Desktop, Documents, cwd, temp.
analyze_har"What's in this capture?" — triage overview, one verdict per check. Start here.
har_briefThe full audit as redacted markdown. The artifact to quote or paste.
har_findingsFindings, worst-first, filterable by severity. Paged.
har_vendorsEvery third party, scored 0–100 by blast radius, with an HTTP Archive scrutiny tier.
har_provenanceWho loaded whom — the fourth parties your vendors brought with them.
har_perf"Why was this slow?" — slowest requests by dominant phase, per-origin handshake cost, uncompressed assets, time lost to redirects.
har_cspA starter Content-Security-Policy synthesized from observed traffic.
har_huntQuery requests — is:thirdparty, status:>=400, type:script, host:…. Returns entry indices.
har_entryEverything about one request: headers, cookies, body, timing phases.
har_curlThat request as a runnable cURL or fetch(), credentials masked.
har_diffBefore vs. after: what was added, what regressed, which third parties are new.
sanitize_harWrite a .redacted.har safe to attach to a ticket.

har_hunt → har_entry → har_curl is the loop: find the request, read it, replay it. Every tool that returns a list takes a limit and tells you the total, so nothing silently returns a first page as if it were the whole answer.

Every tool except sanitize_har is annotated readOnlyHint, and all of them are openWorldHint: false — the no-network guarantee below, in a form your client can read and act on rather than prose you have to take on trust.

Three properties it inherits from the web app

No network. The analyzers contain no fetch, and this transport does not add one. That invariant is the product — Cloudflare shipped a DLP profile in March 2026 that detects HAR files in HTTP traffic and lets admins block the upload outright, because unsanitized HARs are a known credential-exfiltration path.

Summaries, never dumps. Every tool returns a rendered conclusion, not raw entries, and every list is bounded with its total stated. The captures this exists for run to tens of thousands of entries and hundreds of megabytes; handing an agent the entry list would blow its context and make it slower at a job the analyzers already did. (This was a promise the code broke until 0.2.0 — har_findings had no cap and returned ~93,000 tokens on a 10,000-entry capture. The 27-entry demo returned ~175, which is exactly why it went unnoticed.)

Redacted by default. har_brief and har_findings route through the same redactor the browser export uses, built from a single shared secret-pattern table. An agent reading a capture in an editor is more likely to paste a finding into a chat window than a human with a download folder.

What it will not do

  • Overwrite anything. sanitize_har refuses to write over an existing target or the original capture.
  • Read a file above ~512 MB. Guarded rather than left to OOM — pinned just under V8's maximum string length, since the file is read as one string.
  • Answer a query it did not understand. A misspelled filter (is:third-party, staus:404) is an error, not an empty result. Those were the same response until 0.2.0, which meant a typo could report a capture clean.
  • Judge time against your clock. A HAR is a historical artifact, so token expiry is measured against each entry's startedDateTime. Comparing to now marks every token in a week-old capture as expired and buries the one that was genuinely dead when the browser sent it.

Reading the code

This package ships one file, dist/server.js. It is deliberately not minified — the build treats it as something a human debugging an editor integration will read far more often than something a machine will parse for size — so it is the same code a build would produce, already built. There is no separate source repository to clone; the shipped file is the artifact to audit.

License

MIT. Bundled vendor data is generated from third-party-web — MIT, Copyright (c) 2017 Patrick Hulce, derived from HTTP Archive.

Source: README.md at commit 3684af6

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.3.2LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.