Ext Ops Panel
Open dashboard
Comparison

mcp-tunnels vs Runrun.it MCP Server

mcp-tunnels is a plugin bundle for AI coding tools published by Anthropic. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-official). Runrun.it MCP Server is an MCP server published by zNetinho. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-29. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.

Where each is published

Where each is published
Marketplacemcp-tunnelsRunrun.it MCP Server
Claude Code: claude-plugins-official Listed
Version: not stated
Forks (GitHub): 4 698
Stars (GitHub): 45 000
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 1.0.0
Downloads/month (npm): 530
Downloads/week (npm): 49
Forks (GitHub): 0
Stars (GitHub): 0
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

mcp-tunnels vs Runrun.it MCP Server
Factmcp-tunnelsRunrun.it MCP Server
Marketplaces that list it11
Stars (GitHub) (differs)45 000 (better)0 (worse)
Forks (GitHub) (differs)4 698 (better)0 (worse)
Last releaseNot publishedNot published
Where it runs (differs)Installs as a plugin bundleOn your machine (mcp-runrunit)
Transport (differs)Not statedstdio
Tools it declaresNot publishedNot published
Environment variables it asks for (differs)Not published2, secrets among them: 2
Parts of the bundle (differs)1Not a bundle
LicenceNot statedNot stated
Repository (differs)github.com/anthropics/claude-plugins-officialgithub.com/znetinho/plugin-sentinel-mcp
Changes in the last 7 days00
First seen2026-10-112026-10-11

Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.

What each says it does

mcp-tunnels

In its own words, on Claude Code: claude-plugins-official:

Connect Claude to a private MCP server through an Anthropic MCP tunnel. The /create-docker-mcp-tunnel command drives the Docker Compose quickstart end to end: certificates, proxy config, cloudflared, and a verifiable sample server.

Runrun.it MCP Server

In its own words, on Official MCP Registry:

MCP server for Runrun.it: Tasks, Comments, Projects

How to run each

mcp-tunnels As a Claude Code plugin

Claude Code
/plugin install mcp-tunnels@claude-plugins-official

Runrun.it MCP Server As a local MCP server: npm package

Claude Code
claude mcp add --env "RUNRUNIT_APP_KEY=<YOUR_RUNRUNIT_APP_KEY>" --env "RUNRUNIT_USER_TOKEN=<YOUR_RUNRUNIT_USER_TOKEN>" --transport stdio runrunit-n1 -- npx -y mcp-runrunit

Requires: RUNRUNIT_APP_KEY (secret), RUNRUNIT_USER_TOKEN (secret)

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Tools each declares

Neither one's marketplaces publish a list of tools, so there is nothing to compare.

Settings each asks for

The marketplaces of mcp-tunnels publish no settings it asks for, so we do not compare settings.

What it can do: mcp-tunnels · What it can do: Runrun.it MCP Server · Compare two other plugins

Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-official/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built