---
title: Trace Cursor Agents with Langfuse
sidebarTitle: Cursor
logo: /images/integrations/cursor_icon.png
description: Monitor and trace your Cursor AI agent interactions with Langfuse for comprehensive observability and debugging of AI-assisted coding sessions.
category: Integrations
---

# Trace Cursor Agents with Langfuse

This guide shows you how to trace [Cursor](https://cursor.com) AI agent interactions with Langfuse for monitoring, debugging, and analyzing your AI-assisted coding sessions.

> **What is Cursor?** [**Cursor**](https://cursor.com) is an AI-powered code editor built on top of VS Code. It features AI agents that can help you write, edit, debug, and understand code through natural language interactions. Cursor agents can execute shell commands, read and edit files, and use MCP (Model Context Protocol) tools to assist developers.

> **What is Langfuse?** [**Langfuse**](https://langfuse.com) is the open-source AI engineering platform. It helps teams collaboratively debug, analyze, and iterate on their LLM applications with features like tracing, prompt management, and evaluation.

## What This Integration Does

With this integration, you can automatically trace all Cursor agent activity to Langfuse:

- **User Prompts**: Capture every prompt and instruction sent to the agent
- **Agent Responses**: Record all agent responses and reasoning
- **File Operations**: Track file reads and edits with detailed statistics
- **Shell Commands**: Monitor shell command execution and outputs
- **MCP Tool Calls**: Log all MCP tool invocations and results
- **Session Tracking**: Group traces by conversation and workspace for easy filtering
- **Performance Metrics**: Capture latencies, token usage, and execution times

## How It Works

Source: [naoufalelh/cursor-langfuse](https://github.com/naoufalelh/cursor-langfuse)

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/integrations/developer-tools/cursor.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.