Webhook Crash Lab

io.github.Krrishkumar125Published by GitHub account Krrishkumar125v0.2.4Updated Oct 29, 2026

Lets coding agents crash-test webhook handlers and re-run until they survive retries.

VerifiedSTDIODesktop onlyDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

Local MCP server that lets a coding agent crash-test webhook handlers against retries, duplicates and forged signatures, then re-run until they pass.

What you can do
  • Run the crash lab against a config file, optionally with selected scenarios and a report path, returning failures with fix hints in fix order
  • Run a built-in demo in broken or fixed mode to see the loop without any config
  • Explain an existing JSON report, for example one produced in CI
  • List every available scenario with what it checks, why it matters and how to fix it
  • Return results as text plus structured content, with config errors reported as error results rather than crashes
When to use it
Useful when an agent writes or reviews webhook handlers (for example Stripe-style endpoints) and you want a repeatable loop of run, read structured failures, fix and re-run before shipping. Also handy for interpreting a crash-lab report generated in CI.
Requirements
Runs as a local stdio process, typically started with npx from the npm package webhook-crash-lab-mcp; Node.js and network access for the package download are needed. A crash-lab config file (JavaScript or TypeScript) pointing at a target server is required for the main tool; the demo needs no config. No accounts, API keys or environment variables are declared.
Before you install
The config file is executed as code, so only use configs you trust. The tool sends requests to the target named in the config; point it at a local server and a test database and test secret only, never production URLs or live secrets. Reports and failure details are returned to the model.

Installation

In SourceWeft

  1. Open Webhook Crash Lab 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

webhook-crash-lab-mcp

[CI] [npm] [downloads]

Coding agents write webhook handlers that work for one test event and break in production on retries, duplicates and forged signatures. This package gives them a loop: run webhook-crash-lab → read structured failures with fix hints → fix → re-run.

It ships three things:

WhatWhere
MCP serverwebhook-crash-lab-mcp (stdio, official MCP TypeScript SDK)src/
Claude Code pluginskill + MCP server config.claude-plugin/, skills/, .mcp.json
Codex / any-agent skillsame skill in the open Agent Skills format, plus an AGENTS.md snippet.agents/skills/, docs/AGENTS-snippet.md

Tools

ToolInputReturns
run_crash_labconfigPath, cwd?, scenarios?, reportPath?ok, counts, failures[] (id, failed checks, why, fix) in fix order, notTested[], nextSteps[]
run_demomode: "broken" | "fixed"same shape, against the built-in demo app (no config needed)
explain_reportreportPath or report (JSON from webhook-crash-lab run --json)same shape, e.g. for a CI report
list_scenarios–every scenario with what / why / fix

Every result comes back as text for the model and structuredContent (with an outputSchema) for clients. Errors such as a missing or invalid config come back as isError results, not crashes.

60-second start

[Install in VS Code] [Install in Cursor]

Claude Code

sh
claude mcp add webhook-crash-lab -- npx -y [email protected]# or the full plugin (MCP server + skill):#   /plugin marketplace add Krrishkumar125/webhook-crash-lab-mcp#   /plugin install webhook-crash-lab@webhook-crash-lab

Codex

sh
codex mcp add webhook-crash-lab -- npx -y [email protected]mkdir -p .agents/skills && cp -r node_modules/webhook-crash-lab-mcp/.agents/skills/webhook-crash-lab .agents/skills/

Cursor / other MCP clients

json
{  "mcpServers": {    "webhook-crash-lab": { "command": "npx", "args": ["-y", "[email protected]"] }  }}

The examples pin the version so npx never silently runs a newer release. To update, check the latest with npm view webhook-crash-lab-mcp version, read the releases, then change @0.2.4 to the new version in your MCP config and restart the client.

Then ask: "Run the webhook crash lab demo", or "Make my Stripe webhook pass webhook-crash-lab". Paste docs/AGENTS-snippet.md into AGENTS.md / CLAUDE.md to make it a standing rule.

Safety

run_crash_lab imports your crash-lab config (.mjs/.js/.cjs, or .ts/.mts/.cts via the bundled jiti) (it is code, like any config file) and sends requests to its target. Point configs at a local server and a test database and secret only. The skill tells agents never to use production URLs or live secrets.

Related

Sibling packages

Other tools by the same author:

License

MIT © Krrish Kumar

Source: README.md at commit 477feed

Tools

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

Version history

1
  1. v0.2.4LatestOct 29, 2026

Score

50% 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