Language: 日本語English

logfire Plugin

Author
Pydantic
Category
Monitoring
Topics
Monitoring & Observability · AI Agents & AI App Development
First seen
2026-07-09
Last confirmed
2026-07-13
Explanation last updated
2026-07-12

The explanation below is AI-generated. Please verify it against the sources.

logfire is a plugin that adds Logfire observability to Python applications, according to the README. It provides commands to detect frameworks and add instrumentation, investigate errors via Logfire traces, and query traces, logs, and metrics. It also includes a logfire-ui skill for opening Logfire project pages and views, a SKILL.md with core Logfire patterns, and an MCP server for querying Logfire data. It can be installed in Claude Code, Codex, or Cursor.

Overview

Logfire is an observability platform (by Pydantic) for Python applications; this plugin integrates it into Claude Code, Codex, and Cursor via commands, a skill, and an MCP server, according to the README.

What you can do with logfire

  • Detect frameworks (e.g. FastAPI, httpx, asyncpg, SQLAlchemy) and add Logfire instrumentation via /instrument
  • Investigate errors using Logfire traces via MCP with /debug
  • Query traces, logs, and metrics interactively, or add query capabilities to code, with /query
  • Open Logfire project pages, live views, traces, and Explore filters via the logfire-ui skill (in Codex)
  • Use a bundled SKILL.md covering configure, instrument, structured logging, and AI/LLM instrumentation patterns
  • Query Logfire data through the included MCP server, switchable between US and EU regions

Sources

Original description (English)

Add Logfire observability to Python applications with auto-instrumentation for FastAPI, httpx, asyncpg, SQLAlchemy, and more

History of logfire

Back to list