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/bch1212/modelwatchWrote 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/bch1212/modelwatch/modelwatch)<a href="https://agentmods.dev/mcp/bch1212/modelwatch/modelwatch"><img src="https://agentmods.dev/badge/mcp/bch1212/modelwatch/modelwatch/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/bch1212/modelwatch/modelwatch"><img src="https://agentmods.dev/badge/mcp/bch1212/modelwatch/modelwatch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
modelwatch 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 13 lines scan A 15af207b0f99
modelwatch is an MCP server published in the GitHub repository bch1212/modelwatch (0 stars, last pushed 4d ago), with no licence file. 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
llm-latency-tracker
Measured latency, time to first token and uptime for 45 AI inference APIs, by region. Remote server at llmlatency.dev.
vox-mcp
Multi-model AI gateway for MCP clients — routes prompts to Gemini, OpenAI, Anthropic, xAI, DeepSeek, Moonshot, OpenRouter, Cloudflare AI Gateway, Vercel AI Gateway, and local models with conversation memory. Runs locally from the vox-mcp Python package. Needs 19 environment variables to run.
distil
Compression with a quality contract — cache-aware, causally-pruned context compression for agentic runtimes, gated by a statistical non-inferiority test. Runs locally from the distil-llm Python package.
statlyte
Live LLM pricing, context windows and model ids, read from each vendor's own page every 3 hours. Runs locally from the statlyte npm package.
prolog-reasoner
LLM-powered logical reasoning with Prolog - Calculator for logic. Runs locally from the prolog-reasoner Python package.
data-cleaner-agent
Clean messy CSVs with an agentic workflow: an LLM decides the steps, tested code does the work. Runs locally from the agentic-csv-cleaner Python package.