Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/thevibeworks/claude-code-docsnpx agentmods add commands/thevibeworks/claude-code-docs/create-docker-mcp-tunnelWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/thevibeworks/claude-code-docs/create-docker-mcp-tunnel)<a href="https://agentmods.dev/commands/thevibeworks/claude-code-docs/create-docker-mcp-tunnel"><img src="https://agentmods.dev/badge/commands/thevibeworks/claude-code-docs/create-docker-mcp-tunnel.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00026 | $0.04378 |
| Opus 5 | $0.00013 | $0.02189 |
| Sonnet 5 | $0.00005 | $0.00876 |
| Haiku 4.5 | $0.00003 | $0.00438 |
Grade B, and why
create-docker-mcp-tunnel scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 "$DIR/.env" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl https://api.anthropic.com/v1/messages \ This is a copy
100% identical to create-docker-mcp-tunnel — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a Docker MCP tunnel
Drive the MCP tunnels quickstart end to end: from zero to Claude calling a private MCP server through an Anthropic-operated tunnel, using Docker Compose with manually supplied credentials (the shortest path for local testing).
MCP tunnels is in research preview. It is provided "as-is" with no uptime or support commitment and depends on a third-party transport (Cloudflare). Do not put production traffic through this without reading the security model.
You are guiding the user through a mix of local commands you run and Console actions only they can do (creating the tunnel, uploading the CA). Be a careful operator: explain each step briefly, run the commands, check the output, and stop with a clear diagnosis if something fails.
Deployment directory: use $ARGUMENTS if the user passed a path, otherwise
default to ./mcp-tunnel. Refer to it below as $DIR.
What you'll build
A container stack on the user's machine:
- mcp-proxy — Anthropic's proxy. Terminates the inner TLS handshake using a certificate the user controls, validates upstream IPs, routes by hostname.
- cloudflared — the tunnel agent. Outbound-only connection to the Anthropic tunnel edge; shares the proxy's network namespace.
- hello-mcp (optional) — a sample FastMCP server, only if the user has no MCP server of their own to expose yet.
When it's up, the routed server is reachable from Claude at
https://<subdomain>.<tunnel-domain>/<path> with nothing listening on a public
port.
Step 0 — Preflight
Run these and report what's missing before going further:
docker --version && docker compose version && openssl version
- Docker + Docker Compose are required.
openssl1.1.1+ is required (the commands below use-addext, available in 1.1.1+). - Confirm the host has outbound access to
api.anthropic.com:443and the tunnel edge (198.41.192.0/19,2606:4700:a0::/44) on 7844 TCP and UDP. No inbound ports are opened.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 370 lines · 26 tokens per session scan B 78ff0c77ee6c
create-docker-mcp-tunnel is a command published in the GitHub repository thevibeworks/claude-code-docs (40 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 4,378 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). It is 100% identical to create-docker-mcp-tunnel, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
documentation-generator
Generate comprehensive documentation for code and APIs.
ops-k8s
Kubernetes deployment and orchestration.
ops-vps
Deployment to a VPS server (OVH, Hetzner, DigitalOcean, Scaleway, etc.).
stop-admin
Stop local admin panel stack (live or demo).
review
Review the file at $ARGUMENTS for code quality issues.
review-issue
Review and respond to a GitHub issue.