ZBS Index What actually exists in applied AI, with the source next to it

mcp server

io.github.bch1212/modelwatch

Continuous behavioral drift monitoring for LLM apps — catches silent provider model updates.

Description as published by the maintainer. Source

  • version 0.1.1
  • active

active — Most recent push to the repository was 2026-08-03.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
GitHub stars 0 Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. cumulative, all time GitHub
Last commit 2026-08-03 Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. point in time GitHub
Open issues 0 Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. as of fetch GitHub
Latest published version 0.1.1 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-05-09 When the registry record was last updated by its maintainer. point in time Model Context Protocol
First listed in the MCP Registry 2026-05-09 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
repository status active The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. as of fetch GitHub

Where to get it

Related, by what their authors tagged them

  • Cathedral — Persistent Memory for AI Agents — last commit 2026-06-13, shares drift-detection
    Persistent memory and drift detection for AI agents across session restarts.
  • Sipcode — last commit 2026-07-04, shares drift-detection
    Context hygiene for Claude Code: drift detection, re-read dedup, and token analytics.
  • io.github.dcostenco/prism-coder — last commit 2026-08-07, shares drift-detection
    Session memory, knowledge search, Brave Search, Gemini AI, and code transforms for AI agents
  • io.github.dcostenco/prism-mcp — last commit 2026-08-07, shares drift-detection
    Session memory, knowledge search, Brave Search, Gemini AI, and code transforms for AI agents
  • io.github.DrBaher/compare-cli-mcp — last commit 2026-08-03, shares drift-detection
    MCP server for compare-cli: contract version diff/redline and a drift gate as agent tools.
  • Cortex RMCP — last commit 2026-08-05, shares observability
    Self-hosted homelab log intelligence over MCP, CLI, and REST with SQLite/FTS.
  • Cortex RMCP — last commit 2026-08-05, shares observability
    Rust MCP server for homelab logs, syslog, Docker logs, FTS search, and AI transcript correlation.
  • DebugBundle — last commit 2026-07-29, shares observability
    DebugBundle MCP: runtime error reporting, incident response, health checks, and product analytics.
  • com.hyperping/hyperping — last commit 2026-07-30, shares observability
    Uptime, API and server monitoring with outages, reporting, on-call and status pages.
  • dev.llmlatency/llm-latency-tracker — last commit 2026-07-23, shares observability
    Measured latency & uptime for AI inference APIs, by region. Exposes a get_ai_api_latency tool.

These share tags the maintainers applied themselves, such as drift-detection, observability. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

Also from bch1212

How the author describes it

Topics the maintainer set on GitHub: ai-agents, anthropic, claude, drift-detection, llm, llm-monitoring, mcp, mcp-server, model-context-protocol, observability, typescript.

Bring your own setup

We take apart real AI setups every week and show what broke, what cost too much, and what the trace actually said. If you run agents on real work, that is where the useful conversation is.

Join ZBS AI Practice Lab

Sources

  1. bch1212/modelwatch on GitHub — GitHub, observed , trust tier 3.
  2. Official MCP Registry — Model Context Protocol, observed , trust tier 1.