Last9 Observability
Seamlessly bring real-time production context—logs, metrics, and traces—into your local environment to auto-fix code faster.
What is Last9 Observability?
Last9 Observability is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to seamlessly bring real-time production context—logs, metrics, and traces—into your local environment to auto-fix code faster.
Seamlessly bring real-time production context—logs, metrics, and traces—into your local environment to auto-fix code faster.
This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Seamlessly bring real-time production context—logs, metrics,
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @last9/mcp-serverManual Installation
npx -y @last9/mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Last9 Observability
Last9 Observability MCP brings real-time production telemetry — logs, metrics, traces, and service health — directly into your local development environment and AI coding tools. It connects to the Last9 observability platform and exposes tools for querying Prometheus metrics, running log searches, analyzing database performance, inspecting deployment changes, and managing alert configurations. Teams use it to debug production incidents faster by giving AI assistants live infrastructure context alongside their code.
Prerequisites
- A Last9 account with an active organization (app.last9.io)
- A Last9 Refresh Token generated from Settings > API Access in the Last9 dashboard
- Node.js 18 or higher (for the npm-based self-hosted option)
- An MCP-compatible client such as Claude Desktop, Cursor, or Claude Code
Generate a Last9 API token
Log in to app.last9.io, navigate to Settings > API Access, and generate an admin refresh token. Copy this token — you will use it as LAST9_REFRESH_TOKEN.
Choose your installation method
For the hosted HTTP transport (simplest), use the Claude Code CLI to add the server directly via Last9's hosted endpoint. Replace <org_slug> with your organization slug from the Last9 dashboard URL.
claude mcp add --transport http last9 https://app.last9.io/api/v4/organizations/<org_slug>/mcpInstall via npm for self-hosted mode
Alternatively, install the npm package globally to run the server locally with your own credentials.
npm install -g @last9/mcp-server@latestConfigure Claude Desktop for self-hosted mode
Add the server to claude_desktop_config.json using the npm package with your refresh token. For multi-cluster setups, also set LAST9_DATASOURCE to the cluster name.
Verify the connection
Open your MCP client and ask a question about your infrastructure. The server auto-embeds your actual log and trace schema attributes into tool descriptions at startup, so you should see real attribute names in tool hints.
Last9 Observability Examples
Client configuration
Add this to claude_desktop_config.json to run the Last9 MCP server locally using your refresh token.
{
"mcpServers": {
"last9": {
"command": "npx",
"args": ["-y", "@last9/mcp-server@latest"],
"env": {
"LAST9_REFRESH_TOKEN": "your_refresh_token_here"
}
}
}
}Prompts to try
These prompts leverage Last9's observability tools to debug and understand production systems.
- "What is the current error rate for the checkout service?"
- "Show me slow queries on the PostgreSQL database in the last 30 minutes"
- "Run a PromQL query: rate(http_requests_total{status=~'5..'}[5m])"
- "What deployments happened in the last hour that could explain this latency spike?"
- "Discover all databases across our infrastructure and show their connection counts"Troubleshooting Last9 Observability
Authentication fails with 'invalid token' error
Ensure you are using a Refresh Token from Settings > API Access, not a regular API key. Tokens must be admin-level. Regenerate a new token if the existing one has expired.
Tools show generic attribute names instead of your actual schema
The server embeds your log and trace schema at startup. If attributes are generic, the server may not have connected to your cluster. Check that LAST9_DATASOURCE is set correctly for multi-cluster setups.
No data returned for metric queries
Verify your org_slug in the hosted URL matches the slug visible in your Last9 dashboard URL. For self-hosted mode, confirm the refresh token has the correct organization scope.
Frequently Asked Questions about Last9 Observability
What is Last9 Observability?
Last9 Observability is a Model Context Protocol (MCP) server that seamlessly bring real-time production context—logs, metrics, and traces—into your local environment to auto-fix code faster. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Last9 Observability?
Install via npm with the command: npx -y @last9/mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Last9 Observability?
Last9 Observability works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Last9 Observability free to use?
Yes, Last9 Observability is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Last9 Observability Alternatives — Similar Monitoring & Observability Servers
Looking for alternatives to Last9 Observability? 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 Last9 Observability 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 Last9 Observability?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.