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/naoyoshinori/docker-gemini-cliWrote 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/naoyoshinori/docker-gemini-cli/gemini-mcpgateway)<a href="https://agentmods.dev/mcp/naoyoshinori/docker-gemini-cli/gemini-mcpgateway"><img src="https://agentmods.dev/badge/mcp/naoyoshinori/docker-gemini-cli/gemini-mcpgateway/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/naoyoshinori/docker-gemini-cli/gemini-mcpgateway"><img src="https://agentmods.dev/badge/mcp/naoyoshinori/docker-gemini-cli/gemini-mcpgateway.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mcpGateway 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 today.
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
{
"mcpGateway": {
"type": "see",
"url": "http://mcp-gateway:8811"
}
}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.
- today First seen · 6 lines scan A 5dfe9ac6bc6e
mcpGateway is an MCP server published in the GitHub repository naoyoshinori/docker-gemini-cli (18 stars, last pushed today), 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 2026-09-10.
Other mcp servers, from other repositories
better-code-review-graph
Knowledge graph for token-efficient code reviews -- semantic search and call-graph resolution across your codebase. Runs locally from the better-code-review-graph Python package. Needs 4 environment variables to run.
memex
Temporal engineering context for agents via MCP. Runs locally from the stifler-memex-mcp npm package. Needs 4 environment variables to run.
nexus-mcp
Model Context Protocol server for AI CLI agents. Runs locally from the nexus-mcp Python package.
cloud-sql-postgres
A CLI tool for running a toolbox server. Runs locally from the @toolbox-sdk/server npm package.
tokrepo-mcp-server
TokRepo MCP: tokrepodiscover for planning, tokrepoinstallplan before writes, tokrepopush. Runs locally from the tokrepo-mcp-server npm package.
docs-langchain
MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.