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)
Zones, DNS, cache purge, Workers, KV, and R2 through the Cloudflare API.
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": {
"edgeport": {
"command": "npx",
"args": [
"-y",
"@reneturcios/edgeport",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add edgeport -- npx -y @reneturcios/edgeport mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"edgeport": {
"command": "npx",
"args": [
"-y",
"@reneturcios/edgeport",
"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": {
"edgeport": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/edgeport",
"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 6, 2026
The registry name was verified with the GitHub account CloudCorpRecords, 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 (0.1.0) reached the registry 5 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js, Docker 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.
edgeport is a small doorway into a Cloudflare account. From one bin an agent can see which accounts and zones a token can reach, read and change DNS records, purge cached content, and inventory the account's Worker scripts, KV namespaces, and R2 buckets. It runs from the command line or as an MCP server for agents.
A Cloudflare API token is required. Put it in the CLOUDFLARE_API_TOKEN environment variable; it is sent to the API as a Bearer token and never appears in output. Account-scoped tools (Worker scripts, KV, R2) take an account_id argument, and when that is omitted they fall back to CLOUDFLARE_ACCOUNT_ID. When a required variable is missing, the call fails with an error that names it.
This is a core subset of the Cloudflare API, not the whole surface: Workers bindings deep configuration, observability and Logpush, rulesets and firewall rules, Pages and deployments, Stream and Images, AI and Vectorize, and the hosted documentation search tool are out of scope.
npx @reneturcios/edgeport list-zones
Or run the container image:
docker run -i -e CLOUDFLARE_API_TOKEN ghcr.io/cloudcorprecords/edgeport
The container defaults to the MCP server (see below). Pass CLI arguments to use it as a CLI instead.
export CLOUDFLARE_API_TOKEN="your api token"
export CLOUDFLARE_ACCOUNT_ID="your account id" # optional fallback
edgeport list-accounts edgeport list-zones --name example.com edgeport get-zone --zone-id edgeport list-dns --zone-id --type A edgeport purge-cache --zone-id --everything edgeport list-workers edgeport list-kv edgeport list-r2
edgeport --version
Exit codes: 0 on success, 1 when an API call fails (including a missing CLOUDFLARE_API_TOKEN or a success: false envelope), 2 for usage errors.
One bin serves both faces. The mcp subcommand starts a stdio MCP server:
npx -y @reneturcios/edgeport mcp
MCP client configuration:
{
"mcpServers": { "edgeport": { "command": "npx", "args": ["-y", "@reneturcios/edgeport", "mcp"], "env": { "CLOUDFLARE_API_TOKEN": "your api token" } } } }
| Tool | Input | What it returns |
|---|---|---|
list_accounts | per_page (integer, optional) | Accounts the token can access, from the envelope's result. |
list_zones | account_id, name, per_page (all optional) | Zones, optionally filtered by account or name. |
get_zone | zone_id (required) | One zone's details. |
list_dns_records | zone_id (required), type, name, per_page (optional) | DNS records in the zone. |
create_dns_record | zone_id, type, name, content (required), ttl, proxied, comment (optional) | The created record. |
update_dns_record | zone_id, record_id (required), any record field (optional) | The updated record; only the fields given are sent. |
delete_dns_record | zone_id, record_id (required) | The delete result. |
purge_cache | zone_id (required), purge_everything, files, tags, hosts (optional) | The purge result for the zone. |
list_workers_scripts | account_id (optional) | Worker scripts in the account. |
get_worker_script | script_name (required), account_id (optional) | A shape summary only: content type, byte size, body present. The script body is never returned. |
list_kv_namespaces | account_id (optional) | Workers KV namespaces in the account. |
list_r2_buckets | account_id (optional) | R2 buckets in the account. |
Every JSON response is unwrapped from Cloudflare's {success, errors, result} envelope. A success: false envelope is reported as a tool error carrying the API's own error entries.
npm install
npm run build # tsc -> dist/ npm test # node test runner over test/*.test.ts, no network (fake fetch fixtures) npm run dev # run the CLI from source via tsx
MIT — see LICENSE.