MCP Coroot
MCP server for Coroot observability platform - integrate monitoring, troubleshooting, and configuration tools with AI agents
What is MCP Coroot?
MCP Coroot is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for coroot observability platform - integrate monitoring, troubleshooting, and configuration tools with ai agents
MCP server for Coroot observability platform - integrate monitoring, troubleshooting, and configuration tools with AI agents
This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP server for Coroot observability platform - integrate mon
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-corootConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Coroot
MCP Coroot is a Python MCP server that integrates the Coroot open-source observability platform with AI agents, exposing over 60 tools covering application monitoring, distributed tracing, log search, infrastructure metrics, dashboard management, alert integrations, SLO tracking, and cost analysis. DevOps engineers and SREs can use it to ask natural language questions about their production systems — diagnosing latency spikes, searching error logs, or configuring Slack alerts — all directly from an AI client like Claude Desktop.
Prerequisites
- A running Coroot v1.0+ instance accessible over HTTP/HTTPS
- Valid Coroot credentials: username/password, a session cookie (for SSO), or an API key
- Python 3.10+ with uv installed, or Docker for a no-install deployment
- An MCP-compatible AI client such as Claude Desktop
Install mcp-coroot via uvx (recommended)
The easiest way to run mcp-coroot is with uvx, which downloads and runs it in an isolated environment without a global install.
uvx mcp-corootOr install via pip
Install mcp-coroot into your Python environment if you prefer a persistent installation.
pip install mcp-corootGather your Coroot connection details
You will need your Coroot instance URL and one of the supported authentication methods. For standard deployments, username and password are sufficient. SSO users should use a session cookie.
Configure Claude Desktop with Coroot connection details
Add mcp-coroot to your Claude Desktop MCP config. Pass your Coroot URL and credentials as environment variables.
{
"mcpServers": {
"coroot": {
"command": "uvx",
"args": ["mcp-coroot"],
"env": {
"COROOT_BASE_URL": "http://your-coroot-host:8080",
"COROOT_USERNAME": "admin",
"COROOT_PASSWORD": "your-password"
}
}
}
}Restart Claude Desktop and verify connectivity
Restart Claude Desktop. Ask a simple question like 'List my Coroot projects' to confirm the server connects and authenticates successfully.
MCP Coroot Examples
Client configuration
Claude Desktop config for mcp-coroot using basic auth. For SSO, replace COROOT_USERNAME/PASSWORD with COROOT_SESSION_COOKIE.
{
"mcpServers": {
"coroot": {
"command": "uvx",
"args": ["mcp-coroot"],
"env": {
"COROOT_BASE_URL": "http://coroot.internal:8080",
"COROOT_USERNAME": "admin",
"COROOT_PASSWORD": "your-secure-password"
}
}
}
}Prompts to try
Example prompts for AI-driven observability and troubleshooting with Coroot.
- "Search for error logs in the payment-service from the last 30 minutes."
- "What is the p99 latency for the checkout service over the past hour?"
- "Analyze the root cause of the high error rate in the frontend service."
- "Set up a Slack notification for any SLO breach in the production project."
- "Show me the cost breakdown by service for this month."Troubleshooting MCP Coroot
Authentication fails with 401 Unauthorized
Double-check COROOT_USERNAME and COROOT_PASSWORD match the credentials you use to log into Coroot's web UI. If your organization uses SSO or MFA, use COROOT_SESSION_COOKIE instead: copy the session cookie value from your browser's developer tools after logging in.
COROOT_BASE_URL connection refused or timeout
Ensure the URL includes the correct scheme and port (e.g. http://coroot.internal:8080 not just coroot.internal). Verify your machine has network access to the Coroot instance — it may be inside a private network requiring a VPN.
uvx mcp-coroot not found or fails to resolve
Install uv first: curl -LsSf https://astral.sh/uv/install.sh | sh. Then confirm uvx is in your PATH with which uvx. Alternatively, use pip install mcp-coroot and set the command to mcp-coroot in your MCP config.
Frequently Asked Questions about MCP Coroot
What is MCP Coroot?
MCP Coroot is a Model Context Protocol (MCP) server that mcp server for coroot observability platform - integrate monitoring, troubleshooting, and configuration tools with ai agents It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Coroot?
Follow the installation instructions on the MCP Coroot GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCP Coroot?
MCP Coroot works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Coroot free to use?
Yes, MCP Coroot is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
MCP Coroot Alternatives — Similar Monitoring & Observability Servers
Looking for alternatives to MCP Coroot? Here are other popular monitoring & observability servers you can use with Claude, Cursor, and VS Code.
Netdata
★ 78.9kReal-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Kubeshark
★ 11.9keBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.
Mission Control
★ 4.9kSelf-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.
Grafana
★ 3.0kThis MCP server enables natural-language querying of Grafana logs by automatically detecting log sources and service labels. It provides read-only access to log data with intelligent caching for efficient repeat queries.
Sentrux
★ 2.4kReal-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.
OpenInference
★ 986OpenTelemetry Instrumentation for AI Observability
Browse More Monitoring & Observability MCP Servers
Explore all monitoring & observability servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MCP Coroot in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use MCP Coroot?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.