Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/soyrageagency/docker-mcp-serverWrote 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/mcp/soyrageagency/docker-mcp-server/docker)<a href="https://agentmods.dev/mcp/soyrageagency/docker-mcp-server/docker"><img src="https://agentmods.dev/badge/mcp/soyrageagency/docker-mcp-server/docker/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/mcp/soyrageagency/docker-mcp-server/docker"><img src="https://agentmods.dev/badge/mcp/soyrageagency/docker-mcp-server/docker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
docker scanned grade A with 0 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"docker": {
"command": "npx",
"args": [
"-y",
"@soyrageagency/docker-mcp"
],
"env": {
"DOCKER_MCP_READONLY": "false",
"DOCKER_MCP_ALLOW_EXEC": "false",
"DOCKER_MCP_DEFAULT_LOG_TAIL": "200"
}
}
}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.
- 1mo ago Changed · +1 lines f7f3c9ed08ea
- 1mo ago First seen · 13 lines scan A 38f0da7cf991
docker is an MCP server published in the GitHub repository soyrageagency/docker-mcp-server (3 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
docker-mcp-server
MCP server for managing Docker resources via the Docker SDK for Python. Runs locally from the docker-mcp-server Python package.
synapse
Host, Docker, Compose, SSH, logs, ZFS, and file operations over MCP and CLI. Runs locally from the @dinglebear/synapse npm package. Needs 7 environment variables to run.
docker-compose-audit
Security audit for docker-compose.yml — 25 checks: secrets, privileges, network, volumes, images. Remote server at unbearable-dev--docker-compose-audit.apify.actor.
docker-mcp
MCP server for managing Docker containers, images, networks, volumes, and registries. Runs locally from the @alisaitteke/docker-mcp npm package.
mcp-server
Secure Firecracker microVM sandboxes for AI agents: network policy, PII & injection guardrails. Runs locally from the @declaw/mcp-server npm package. Needs 2 environment variables to run.
mealie-mcp
Mealie MCP Server for Agentic AI! Runs locally from the mealie-mcp Python package.