Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Debug bunny.net CDN pull zones and manage bunny Shield: WAF, rate limits, bot detection, event logs
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.
BUNNY_API_KEY, BUNNY_READONLYValues marked secret are keys to your account. Never share them or paste them into a chat.
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": {
"bunny": {
"command": "npx",
"args": [
"-y",
"@fullfatthings/bunny-mcp"
],
"env": {
"BUNNY_API_KEY": "your-value",
"BUNNY_READONLY": "your-value"
}
}
}
}Run this in your terminal
claude mcp add bunny --env BUNNY_API_KEY=your-value --env BUNNY_READONLY=your-value -- npx -y @fullfatthings/bunny-mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"bunny": {
"command": "npx",
"args": [
"-y",
"@fullfatthings/bunny-mcp"
],
"env": {
"BUNNY_API_KEY": "your-value",
"BUNNY_READONLY": "your-value"
}
}
}
}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": {
"bunny": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@fullfatthings/bunny-mcp"
],
"env": {
"BUNNY_API_KEY": "your-value",
"BUNNY_READONLY": "your-value"
}
}
}
}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.
BUNNY_READONLY envThese 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 7, 2026
The registry name was verified with the GitHub account fullfatthings, 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.
You need to fill in: BUNNY_API_KEY
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 (1.0.1) reached the registry 3 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: Spec Driven Development, Remote Desktop Commander, Aiterm 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
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Persistent terminals and one launcher for Claude, Codex, Grok, Cursor, and Antigravity harnesses.
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.
An MCP server for debugging bunny.net CDN sites and managing bunny Shield, the bunny.net web application firewall (WAF).
This is an unofficial project. It is not affiliated with or endorsed by bunny.net.
It covers pull zones (CDN sites), edge rules, cache purges, CDN statistics, origin error logs, and Shield: WAF settings, custom WAF rules, rate limits, bot detection and WAF event logs. It does not cover DNS, storage, Stream or edge scripts. For those, see anvme/bunnycdn-mcp or Digitizers/bunny-mcp.
get_shield_zone returns notes that warn, for example, when Block rules only log because the zone's WAF execution mode is Log.shield_event_logs shows what the WAF blocked, challenged or logged in the last 72 hours, grouped by rule, IP, JA4 fingerprint and more.update_pull_zone also lists settings bunny.net changed that you did not ask for.detail: true for the raw response.Authorization values in edge rule triggers are replaced with , also in raw responses.Claude Code:
claude mcp add bunny --env BUNNY_API_KEY=your-key -- npx -y @fullfatthings/bunny-mcp
Other MCP clients (for example Claude Desktop):
{
"mcpServers": { "bunny": { "command": "npx", "args": ["-y", "@fullfatthings/bunny-mcp"], "env": { "BUNNY_API_KEY": "your-key" } } } }
| Variable | Meaning |
|---|---|
BUNNY_API_KEY | Required. Your bunny.net account API key. |
BUNNY_READONLY | Set to 1 to register only the read tools. Write tools are then absent from the tool list, so the assistant cannot call them. |
Read tools:
| Tool | Purpose |
|---|---|
list_pull_zones | List pull zones with IDs, origins and hostnames. |
get_pull_zone | One pull zone: hostnames, readable edge rules, and caching, origin and security settings. |
cdn_statistics | Bandwidth, requests, cache hit rate and error responses. |
origin_errors | Failed requests from bunny.net to your origin on one day, with counts by error. |
get_shield_zone | WAF settings, custom rules, rate limits and bot detection, with notes. |
shield_event_logs | Requests the WAF blocked, challenged or logged in the last 72 hours. |
Write tools (not registered when BUNNY_READONLY=1):
| Tool | Purpose |
|---|---|
update_pull_zone | Change pull zone settings. |
purge_cache | Purge one URL or a whole pull zone. |
save_edge_rule | Create or update an edge rule. |
set_edge_rule_enabled | Switch an edge rule on or off. |
delete_edge_rule | Delete an edge rule. |
update_shield_zone | Change WAF settings, including adding or removing single rule IDs from lists. |
update_bot_detection | Change bot detection mode and sensitivity. |
save_waf_rule | Create or update a custom WAF rule. |
save_rate_limit | Create or update a rate limit. |
delete_shield_rule | Delete a custom WAF rule or rate limit. |
To test a new WAF rule safely, save it with action Log, check shield_event_logs, then save it again with action Block.
npm install
npm test
To release, run npm version patch (or minor or major). It updates package.json and server.json, commits, tags and pushes; the tag starts a GitHub Action that publishes to npm and the MCP registry.
MIT. See LICENSE.