Pydantic

Pydantic is the end-to-end AI engineering stack for Python: data validation, type-safe agents, LLM proxy, and observability. This A2A card represents the Pydantic Logfire MCP server, the primary agent-callable surface for the Pydantic platform.

Skills

• Query telemetry data
  Run SQL SELECT queries against a Logfire project's traces, logs, metrics, and exceptions for investigation and exploration.
  observabilitytelemetrysqllogfire
• Manage dashboards
  Create, read, update, and delete Logfire dashboards and their panels, variables, and layout groups using Perses-compatible JSON.
  observabilitydashboardslogfire
• Manage alerts
  Configure SQL-based alerts that periodically run and notify channels when results match. Inspect alert history and current firing state.
  alertsmonitoringlogfire
• Manage feature flags
  Create and update managed variables (feature flags), version snapshots, rollouts, targeting overrides, and labels.
  feature-flagsrolloutslogfire
• Manage notification channels
  Create and update Slack, Discord, Opsgenie, and webhook notification channels for alerts.
  notificationslogfire
• Execute Python in a sandbox
  Run Python code in a secure sandbox with access to Logfire platform helper functions for advanced analysis.
  pythonsandboxlogfire

How to call

https://logfire.pydantic.dev/mcp