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/open-covenant/covenantWrote 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/open-covenant/covenant/hermes-mcp-bridge-mizuki)<a href="https://agentmods.dev/mcp/open-covenant/covenant/hermes-mcp-bridge-mizuki"><img src="https://agentmods.dev/badge/mcp/open-covenant/covenant/hermes-mcp-bridge-mizuki/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/open-covenant/covenant/hermes-mcp-bridge-mizuki"><img src="https://agentmods.dev/badge/mcp/open-covenant/covenant/hermes-mcp-bridge-mizuki.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
Grade A, and why
mizuki 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 2d 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
{
"mizuki": {
"command": "npx",
"args": [
"-y",
"mizuki-mcp"
],
"env": {
"MIZUKI_API_URL": "",
"MIZUKI_API_TOKEN": "",
"MIZUKI_MCP_TIMEOUT_MS": ""
}
}
}What else server.json configures
This page is one entry in a file that holds 2. Installing the file brings all of them; each is measured and scanned on its own page.
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.
- 2d ago First seen · 14 lines scan A f6aac3885ae7
mizuki is an MCP server published in the GitHub repository open-covenant/covenant (8 stars, last pushed today), licensed Apache-2.0. 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 2026-09-14.
Other mcp servers, from other repositories
octopus-blackboard
Shared memory & coordination for AI coding agents — a blackboard, not an orchestrator. Runs locally from the octopus-blackboard npm package. Needs 2 environment variables to run.
keelen
Autonomous dev team steered from chat: plain-English requests in, tested merged PRs out. Remote server at keelen.ai.
stipend
Non-custodial USDC wallet on Base with spending limits enforced in code, not in a prompt. Runs locally from the stipend npm package.
playwright
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
polymarket-guard
Polymarket prediction markets — buy/sell positions in USDC. LemonCake pay-per-call billing. Runs locally from the polymarket-guard-mcp npm package. Needs 2 environment variables to run.
xstocks
Buy tokenized US stocks (xStocks) on Solana via Jupiter DEX in USDC. Daily cap. Dry-run default. Runs locally from the xstocks-mcp npm package. Needs 2 environment variables to run.