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.
npx agentmods add mcp/phenomenoner/adaptive-agent-harness/adaptive-agent-runtime-aargit clone --depth 1 https://github.com/phenomenoner/adaptive-agent-harnessWrote 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/phenomenoner/adaptive-agent-harness/adaptive-agent-runtime-aar)<a href="https://agentmods.dev/mcp/phenomenoner/adaptive-agent-harness/adaptive-agent-runtime-aar"><img src="https://agentmods.dev/badge/mcp/phenomenoner/adaptive-agent-harness/adaptive-agent-runtime-aar.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
aar 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 4d 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
{
"aar": {
"args": [],
"command": "aar-codex-mcp",
"startup_timeout_sec": 30,
"tool_timeout_sec": 60
}
}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.
- 4d ago First seen · 8 lines scan A 0341f7a7eca3
aar is an MCP server published in the GitHub repository phenomenoner/adaptive-agent-harness (1 stars, last pushed 4d 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
technocore-chat
MCP server for technocore-chat: shared rooms, durable notes and rendezvous for agents, over plain HTTP. Runs locally from the technocore-mcp Python package. Needs 2 environment variables to run.
guard
MCP server "guard" as configured in open-covenant/covenant. Launched with https://github.com/open-covenant/covenant/releases/download/covguard-v0.1.1/cove.
search
MCP server for searching Airweave collections with natural language queries. Runs locally from the airweave-mcp-search npm package. Needs 3 environment variables to run.
agent-control-plane
Layer 3: The Framework - A governance and management layer for autonomous AI agents. Runs locally from the agent-control-plane Python package.
sitepulsar
MCP server "sitepulsar", hosted remotely at mcp.sitepulsar.ai, as configured in SitePulsar/mcp-server.
netid
MCP server "netid" as configured in route6me/mcp. Runs in Docker (docker.io/route6me/netid:1.2.4).