1. Conduid
  2. Agents
  3. Claudewatch
MCP server · Agents

Claudewatch

by · github.com/blackwell-systems/claudewatch

AgentOps for Claude Code. Monitors AI agent behavior during development: real-time error loops, drift detection, friction analysis. Claude gets self-awareness hooks + MCP tools. You get cost-per-commit, agent success rates, exportable metrics. Like DevOps, but for AI agents.

Unclaimed last commit 7 months ago agentic-workflowaiai-agentsai-observabilityaiopsanalyticsanthropicclaudeclaude-codeclideveloper-toolsgogolangllmllm-agentsmcpmcp-serverobservabilitysession-analyticssqlite
InstallView source
34Low

Scored 21 days ago · breakdown

About Claudewatch

Claudewatch is an MCP server published by blackwell-systems in the Agents category: agentOps for Claude Code. Monitors AI agent behavior during development: real-time error loops, drift detection, friction analysis. Claude gets self-awareness hooks + MCP tools. You get cost-per-commit, agent success rates, exportable metrics. Like DevOps, but for AI agents.

The repository has 9 stars and 0 forks, with the last commit 7 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/blackwell-systems/claudewatch

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Claudewatch

Powered by Claude · Grounded in docs

I know everything about Claudewatch. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Releases

v0.15.0v0.15.0 · 5 Mar 2026Changelog 2ebb1ce1315c1bd2b81b27c978e177199d560b5d feat(cli): add context command for unified context search 47f46751f596eac06615a7239ff332679237c463 feat(cli): implement full unified context search integration…
v0.14.0v0.14.0 · 5 Mar 2026Phase 2: Guardrails — Prevent Bad Behavior Added Repetitive error detection in PostToolUse hook — New Priority 1.5 check. `ParseLiveRepetitiveErrors` tracks per-(tool, error-pattern) tuples. Warns at 3rd consecutive same-tool same-error,…
v0.13.0v0.13.0 · 5 Mar 2026Per-model cost accuracy, expanded hooks, and rules migration Added Expanded startup briefing — SessionStart hook shows tool error averages, 0% success agent warnings, and blocker counts Contextual memory surfacing — Auto-extracts…
v0.12.0v0.12.0 · 4 Mar 2026Changelog 279242049c82783ab9dd99be6859cb0396fc489c Merge wave1-agent-A: Prometheus exporter interface + implementation 7995ac14aa40cdd0b191a2e082374f1d8da9bd50 Merge wave1-agent-A: active session discovery…
v0.11.0v0.11.0 · 4 Mar 2026Changelog 1f3dbcffdd081a9deb78e2fa643daa60fc121ad9 feat: automated MCP server setup in install command
Questions

About Claudewatch

How do I install Claudewatch?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Claudewatch safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Claudewatch still maintained?

The last commit was 7 months ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.