GitHub
GitHub’s official server lets AI read and manage code, issues and pull requests in your account. Use GitHub’s hosted version or run it locally with Docker.
Description from the maker (original English)
Lets coding agents crash-test webhook handlers and re-run until they survive retries.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"webhook-crash-lab": {
"command": "npx",
"args": [
"-y",
"webhook-crash-lab-mcp"
]
}
}
}Run this in your terminal
claude mcp add webhook-crash-lab -- npx -y webhook-crash-lab-mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"webhook-crash-lab": {
"command": "npx",
"args": [
"-y",
"webhook-crash-lab-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"webhook-crash-lab": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"webhook-crash-lab-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026
The registry name was verified with the GitHub account Krrishkumar125, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.2.4) reached the registry 9 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: GitHub, Desktop Commander, Cloudflare MCP
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
GitHub’s official server lets AI read and manage code, issues and pull requests in your account. Use GitHub’s hosted version or run it locally with Docker.
MCP server for terminal commands, file operations, and process management
Cloudflare MCP servers
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
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](https://github.com/Krrishkumar125/webhook-crash-lab) → read structured failures with fix hints → fix → re-run.
It ships three things:
| What | Where | |
|---|---|---|
| MCP server | webhook-crash-lab-mcp (stdio, official MCP TypeScript SDK) | src/ |
| Claude Code plugin | skill + MCP server config | .claude-plugin/, skills/, .mcp.json |
| Codex / any-agent skill | same skill in the open Agent Skills format, plus an AGENTS.md snippet | .agents/skills/, docs/AGENTS-snippet.md |
| Tool | Input | Returns | |
|---|---|---|---|
run_crash_lab | configPath, cwd?, scenarios?, reportPath? | ok, counts, failures[] (id, failed checks, why, fix) in fix order, notTested[], nextSteps[] | |
run_demo | `mode: "broken" \ | "fixed"` | same shape, against the built-in demo app (no config needed) |
explain_report | reportPath 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.
Claude Code
claude mcp add webhook-crash-lab -- npx -y webhook-crash-lab-mcp@0.2.4
Codex
codex mcp add webhook-crash-lab -- npx -y webhook-crash-lab-mcp@0.2.4
mkdir -p .agents/skills && cp -r node_modules/webhook-crash-lab-mcp/.agents/skills/webhook-crash-lab .agents/skills/
Cursor / other MCP clients
{
"mcpServers": { "webhook-crash-lab": { "command": "npx", "args": ["-y", "webhook-crash-lab-mcp@0.2.4"] } } }
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.
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.
Other tools by the same author:
MIT © Krrish Kumar