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/APantov/llm-routing-comparisonWrote 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/apantov/llm-routing-comparison/llm-routing)<a href="https://agentmods.dev/mcp/apantov/llm-routing-comparison/llm-routing"><img src="https://agentmods.dev/badge/mcp/apantov/llm-routing-comparison/llm-routing/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/apantov/llm-routing-comparison/llm-routing"><img src="https://agentmods.dev/badge/mcp/apantov/llm-routing-comparison/llm-routing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
llm-routing 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 9d 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
{
"llm-routing": {
"command": "python",
"args": [
"-m",
"router_agent.mcp_server"
],
"env": {
"ROUTER_LADDER": "wide",
"ROUTER_MODE": "replay",
"ROUTER_K": "3",
"ROUTER_AGREEMENT": "1.0"
}
}
}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.
- 9d ago First seen · 15 lines scan A 172db728c0f7
llm-routing is an MCP server published in the GitHub repository APantov/llm-routing-comparison (0 stars, last pushed 17d 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
vessel-browser
AI-native browser runtime for autonomous agents with human-in-the-loop supervision. Runs locally from the @quanta-intellect/vessel-browser npm package.
dos-kernel
Dispatch Operating System — the domain-free trust substrate for fleets of autonomous agents (verdict spine, ship oracle, structured refusal, lane arbiter, correlation spine). Runs locally from the dos-kernel Python package. Needs 1 environment variable to run.
kiagent
Your mail, chats and documents indexed into a local SQLite corpus, served to AI clients over MCP. Remote server at {subdomain}.localkiagent.com.
prove
MCP server "prove" as configured in whenpoem/aiscientist. Launched with uv tool run --from claudescientist[all]==5.1.4 claudescientist mcp prove.
tgms
Agent-Native Temporal Graph Management System (bi-temporal property graph + validated temporal operator algebra + PEV agent layer). Runs locally from the tgms Python package.
kafka-sentinel-mcp
Read-only Kafka observability MCP server: cluster health, consumer lag, and replay-readiness for AI agents that must never touch production. Runs locally from the kafka-sentinel-mcp Python package. Needs 6 environment variables to run.