This repository contains a Model Context Protocol (MCP) server with tools that can access the OpenTelemetry traces and metrics you've sent to Pydantic Logfire. Pydantic Logfire provides a hosted remote MCP server that you can use instead of running this package locally. This is the easiest way to get started with the Logfire MCP server. To use the remote MCP server, add the following configuration
Add this skill
npx mdskills install pydantic/logfire-mcpWell-documented remote MCP server with clear multi-client setup but lacks tool capability details
This repository contains a Model Context Protocol (MCP) server with tools that can access the OpenTelemetry traces and metrics you've sent to Pydantic Logfire.
Pydantic Logfire provides a hosted remote MCP server that you can use instead of running this package locally. This is the easiest way to get started with the Logfire MCP server.
To use the remote MCP server, add the following configuration to your MCP client.
Choose the endpoint that matches your Logfire data region:
logfire-us.pydantic.devlogfire-eu.pydantic.devFor US region (logfire-us.pydantic.dev):
{
"mcpServers": {
"logfire": {
"type": "http",
"url": "https://logfire-us.pydantic.dev/mcp"
}
}
}
For EU region (logfire-eu.pydantic.dev):
{
"mcpServers": {
"logfire": {
"type": "http",
"url": "https://logfire-eu.pydantic.dev/mcp"
}
}
}
Note:
The remote MCP server handles authentication automatically through your browser. When you first connect, you'll be prompted to authenticate with your Pydantic Logfire account.
Note:
If you want to run logfire-mcp locally, check the OLD_README.md file.
The examples below use the US region endpoint. Replace the URL with https://logfire-eu.pydantic.dev/mcp if you are using the EU region.
Create a .cursor/mcp.json file in your project root:
{
"mcpServers": {
"logfire": {
"type": "http",
"url": "https://logfire-us.pydantic.dev/mcp"
}
}
}
Run the following command:
claude mcp add logfire --transport http https://logfire-us.pydantic.dev/mcp
Add to your Claude settings:
{
"mcpServers": {
"logfire": {
"type": "http",
"url": "https://logfire-us.pydantic.dev/mcp"
}
}
}
Add to your Cline settings in cline_mcp_settings.json:
{
"mcpServers": {
"logfire": {
"type": "http",
"url": "https://logfire-us.pydantic.dev/mcp"
}
}
}
Make sure you enabled MCP support in VS Code.
Create a .vscode/mcp.json file in your project's root directory:
{
"servers": {
"logfire": {
"type": "http",
"url": "https://logfire-us.pydantic.dev/mcp"
}
}
}
Create a .zed/settings.json file in your project's root directory:
{
"context_servers": {
"logfire": {
"type": "http",
"url": "https://logfire-us.pydantic.dev/mcp"
}
}
}
Install via CLI
npx mdskills install pydantic/logfire-mcpPydantic Logfire MCP Server is a free, open-source AI agent skill. This repository contains a Model Context Protocol (MCP) server with tools that can access the OpenTelemetry traces and metrics you've sent to Pydantic Logfire. Pydantic Logfire provides a hosted remote MCP server that you can use instead of running this package locally. This is the easiest way to get started with the Logfire MCP server. To use the remote MCP server, add the following configuration
Install Pydantic Logfire MCP Server with a single command:
npx mdskills install pydantic/logfire-mcpThis downloads the skill files into your project and your AI agent picks them up automatically.
Pydantic Logfire MCP Server works with Claude Code, Claude Desktop, Cursor, Vscode Copilot, Windsurf, Continue Dev, Gemini Cli, Amp, Roo Code, Goose. Skills use the open SKILL.md format which is compatible with any AI coding agent that reads markdown instructions.