Langfuse Observability
Langfuse Observability monitors your code in real-time, surfacing errors and performance issues instantly to accelerate debugging & improve application health.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add langfuse-observability npx -- -y @trustedskills/langfuse-observability
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"langfuse-observability": {
"command": "npx",
"args": [
"-y",
"@trustedskills/langfuse-observability"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill integrates observability into AI agent workflows using Langfuse. It allows you to track and analyze agent performance, including tracing function calls, measuring execution times, and identifying bottlenecks. This provides valuable insights for debugging, optimization, and improving overall agent efficiency.
When to use it
- Debugging slow agents: Identify which functions or steps are contributing most to long execution times.
- Monitoring production agents: Track key performance indicators (KPIs) like average response time and error rates over time.
- Analyzing complex workflows: Understand the flow of data and control within an agent's actions.
- Optimizing resource usage: Pinpoint areas where resources are being wasted or inefficiently utilized.
Key capabilities
- Integration with Langfuse observability platform
- Function call tracing
- Execution time measurement
- Performance bottleneck identification
Example prompts
- "Enable Langfuse observability for this agent."
- "Show me the average execution time of the 'send_email' function."
- "What are the top 5 slowest functions called by this agent?"
Tips & gotchas
Requires a Langfuse account and API key to function correctly. Ensure proper configuration with your agent’s environment for accurate data collection.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🏢 Official
Published by the company or team that built the technology.