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/MidOSresearch/midosWrote 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/midosresearch/midos/midos)<a href="https://agentmods.dev/mcp/midosresearch/midos/midos"><img src="https://agentmods.dev/badge/mcp/midosresearch/midos/midos/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/midosresearch/midos/midos"><img src="https://agentmods.dev/badge/mcp/midosresearch/midos/midos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
midos 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
{
"midos": {
"command": "uvx",
"args": [
"midos-mcp"
],
"env": {
"MIDOS_API_KEY": ""
}
}
}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 First seen · 11 lines scan A fe673764ea56
midos is an MCP server published in the GitHub repository MidOSresearch/midos (8 stars, last pushed 5mo 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
superskill
One-entry orchestrator for coding agents: jailed vault, FTS knowledge graph, 18-axis review, in-harness Chrome QA. Curated packs — not a 90k-skill dump. Runs locally from the superskill npm package.
mako-ai
Agentmako is a local project intelligence CLI and MCP server for codebases and databases, with repo-aware indexing, schema snapshots, and secure live database connectivity. Runs locally from the agentmako npm package.
pg-context-mcp
MCP server "pg-context-mcp" as configured in mewsyy/pg-context. Runs locally from the pg-context-mcp npm package.
aedile
Maintains architectural integrity as AI writes code. Runs locally from the aedile Python package.
llm-bus
Coordinate multiple AI agents over MCP: atomic claims, leases, shared ledger, handoffs, tasks. Remote server at mcp.llm-bus.com.
token-pilot
Save up to 80% tokens when AI reads code via AST-aware structural reading. Runs locally from the token-pilot npm package.