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/ronmkr/PromptBooknpx agentmods add commands/ronmkr/promptbook/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/ronmkr/promptbook/create-docker-mcp-tunnel)<a href="https://agentmods.dev/commands/ronmkr/promptbook/create-docker-mcp-tunnel"><img src="https://agentmods.dev/badge/commands/ronmkr/promptbook/create-docker-mcp-tunnel/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ronmkr/promptbook/create-docker-mcp-tunnel"><img src="https://agentmods.dev/badge/commands/ronmkr/promptbook/create-docker-mcp-tunnel.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00025 | $0.04366 |
| Opus 5 | $0.00013 | $0.02183 |
| Sonnet 5 | $0.00005 | $0.00873 |
| Haiku 4.5 | $0.00003 | $0.00437 |
Grade B, and why
create-docker-mcp-tunnel scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 "$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.platform.local/v1/messages \ 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 Gemini calling a private MCP server through an Google-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 — Google'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 Google 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 Gemini 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.platform.local: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.
- 9d ago First seen · 370 lines · 25 tokens per session scan B 8f222baba001
create-docker-mcp-tunnel is a command published in the GitHub repository ronmkr/PromptBook (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 4,366 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). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.