What is the kitaru MCP server?

zenml-io/kitaru — Agent traces you can run, not just read. AgentRank score: 87.0/100.

Is the kitaru MCP server actively maintained?

The kitaru MCP server was last committed 1mo ago and has 16 contributors. Issue health: 86% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

kitaru MCP Server

Name: zenml-io/kitaru
Rating: 4.5 (1 reviews)
Author: zenml-io

zenml-io/kitaru

Score: 87.0 → 0% Rank #612 Monitoring

[![AgentRank](https://agentrank-ai.com/api/v1/badge/zenml-io--kitaru)](https://agentrank-ai.com/tool/zenml-io--kitaru/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

Are you the maintainer of zenml-io/kitaru? Claim this listing →

Agent traces you can run, not just read.

Add AgentRank to Claude Code Discover and compare tools like zenml-io/kitaru — your AI finds the right one automatically

Get API Access →

claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

zenml-io/kitaru is a Python tool licensed under Apache-2.0. Agent traces you can run, not just read. Topics: ai-agents, checkpoints, durable-execution, llm, mcp, mlops, observability, pydantic, pydantic-ai, python, replay, agent, agent-orchestration, agentic-ai, agents.

Ranked #612 out of 24846 indexed tools.

In the top 3% of all indexed tools.

Has 16 contributors.

Ecosystem

Python Apache-2.0 2,169 pypi/wk

ai-agentscheckpointsdurable-executionllmmcpmlopsobservabilitypydanticpydantic-aipythonreplayagentagent-orchestrationagentic-aiagents

Score Breakdown

Stars 15% 307

307 stars → growing community

Freshness 25% 1mo ago

Last commit 1mo ago → recently updated

Issue Health 25% 86%

248/290 issues closed → responsive maintainer

Contributors 10% 16

16 contributors → active community

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads 13% 2,169/wk

2,169 weekly installs → gaining traction

Forks 26

Description Brief

License Apache-2.0

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

Badge all embed codes →

Markdown

[![AgentRank](https://agentrank-ai.com/api/v1/badge/zenml-io--kitaru)](https://agentrank-ai.com/tool/zenml-io--kitaru/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

<a href="https://agentrank-ai.com/tool/zenml-io--kitaru/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/zenml-io--kitaru" alt="AgentRank"></a>

Embed Widget docs →

HTML

<script src="https://agentrank-ai.com/embed.js" data-tool="zenml-io/kitaru"></script>

Details

Stars: 307
Forks: 26
Open Issues: 42
Closed Issues: 248
Contributors: 16
Dependents: —
Language: Python
License: Apache-2.0
Last Commit: 1mo ago

Matched Queries

topic:mcp

From the README

<p align="center">
  <a href="https://docs.zenml.io/kitaru">
    
  </a>
</p>

<h3 align="center">Traces you can run, not just read.</h3>

<p align="center">
  Kitaru (来る, "to arrive") gives you replay-based evals for AI agents. Record or import production runs as sessions, replay them against your next model, prompt, or code change, and see what improved and what broke before you ship. Open source, self-hosted, Python and TypeScript. From the team behind <a href="https://zenml.io">ZenML</a>.
</p>

<p align="center">
  <a href="https://pypi.org/project/kitaru/"></a>
  <a href="https://pypi.org/project/kitaru/"></a>
  <a href="https://github.com/zenml-io/kitaru/blob/main/LICENSE"></a>
</p>

<p align="center">
  <a href="https://docs.zenml.io/kitaru">Docs</a> &middot;
  <a href="https://youtu.be/aYLfzXEr2Rk">Guided Tour</a> &middot;
  <a href="#-get-started">Get Started</a> &middot;
  <a href="https://www.zenml.io/roadmap">Roadmap</a> &middot;
  <a href="https://kitaru.ai/slack">Communit

Read full README on GitHub →

See alternatives to zenml-io/kitaru → Browse monitoring category → Best Monitoring MCP servers → Compare zenml-io/kitaru → Best MCP Servers for DevOps & Infrastructure →How to Choose an MCP Server in 2026 →

View on GitHub →