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/bch1212/modelwatch/modelwatchgit clone --depth 1 https://github.com/bch1212/modelwatchGrade 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 yesterday.
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.
- yesterday First seen · 13 lines scan A 15af207b0f99
modelwatch is an MCP server published in the GitHub repository bch1212/modelwatch (0 stars, last pushed 8d 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
prism-coder
Session memory for coding agents: local-first recall, drift detection, on-device inference. Runs locally from the prism-mcp-server npm package. Needs 8 environment variables to run.
prism-mcp
Persistent session memory for AI coding agents that never leaves your machine — including the on-device model that reasons over it. Restores your prior decisions, open TODOs, and changed files across sessions; adds associative recall of related past work. Runs locally from the prism-mcp-server npm package.
docguard
Deterministic doc-drift detection: guard, score, explain, verify-claims and diagnose MCP tools. Runs locally from the docguard-cli npm package.
cladding
MCP server "cladding" as configured in qwerfunch/cladding. Runs .cladding/host/serve.cjs with node.
token-reconciler
Find where your design-token sources disagree. Point it at a Figma export and a live-site scan (any DTCG files) and it shows you exactly which tokens have drifted, how much it matters, and gives you a clean diff to act on. Runs locally from the token-reconciler npm package.
praxis
Functionalities such as a layers for building neural networks in Jax. Runs locally from the praxis Python package.