Logfire MCP Server

What does “Logfire” MCP Server do?

The Logfire MCP Server is a Model Context Protocol (MCP) server that allows AI assistants and LLMs to access, retrieve, and analyze telemetry data sent to Logfire via the OpenTelemetry standard. By connecting your Logfire project, this server lets AI-driven tools and agents query distributed traces, inspect exception patterns, and run custom SQL queries over your application’s metrics and tracing data using the Logfire APIs. This integration enables rapid troubleshooting, observability, and the automation of common telemetry analysis tasks, providing developers with enhanced workflows for debugging, monitoring, and insight generation directly from their development environments or AI-assisted agents.

List of Prompts

No explicit prompt templates are documented in the repository.

List of Resources

No explicit resources (as MCP resources) are documented in the repository.

List of Tools

• find_exceptions
  Retrieves exception counts from traces, grouped by file, within a specified time window.

• find_exceptions_in_file
  Provides detailed trace information about exceptions occurring in a specific file over a given timeframe.

• arbitrary_query
  Executes custom SQL queries on OpenTelemetry traces and metrics, allowing flexible data exploration.

• get_logfire_records_schema
  Returns the OpenTelemetry schema, enabling users to craft more precise custom queries.

Use Cases of this MCP Server

• Exception Monitoring and Analysis
  Developers can quickly surface which files are generating the most exceptions, identify trends, and focus debugging efforts.

• Root Cause Analysis
  By drilling down into exception details within a specific file, teams can accelerate the identification and resolution of critical issues.

• Custom Telemetry Reporting
  The ability to run arbitrary SQL queries empowers teams to generate bespoke metrics reports and dashboards tailored to their unique needs.

• Schema Exploration
  With access to the OpenTelemetry schema, developers can better understand the available data fields to optimize custom queries and integrations.

How to set it up

Windsurf

No setup instructions provided for Windsurf.

Claude

1. Open Claude Desktop settings.
2. Add a new MCP server configuration with the following JSON:

   {
     "command": ["uvx"],
     "args": ["logfire-mcp"],
     "type": "stdio",
     "env": {
       "LOGFIRE_READ_TOKEN": "YOUR_TOKEN"
     }
   }
   

3. Replace "YOUR_TOKEN" with your actual Logfire read token.
4. Save settings and restart Claude.
5. Verify the MCP server is connected by attempting a query.

Securing API Keys:
Store your token in the env section as above to keep it out of arguments and source control.

Cursor

1. Ensure you have uv installed.
2. Create a .cursor/mcp.json file in your project root.
3. Add the following configuration:

   {
     "mcpServers": {
       "logfire": {
         "command": "uvx",
         "args": ["logfire-mcp", "--read-token=YOUR-TOKEN"]
       }
     }
   }
   

4. Replace "YOUR-TOKEN" with your actual Logfire read token.
5. Save the file and restart Cursor.

Note: Cursor does not support the env field; use the --read-token argument instead.

Cline

1. Open or create cline_mcp_settings.json.
2. Add the following:

   {
     "mcpServers": {
       "logfire": {
         "command": "uvx",
         "args": ["logfire-mcp"],
         "env": {
           "LOGFIRE_READ_TOKEN": "YOUR_TOKEN"
         },
         "disabled": false,
         "autoApprove": []
       }
     }
   }
   

3. Replace "YOUR_TOKEN" with your Logfire read token.
4. Save the file and restart Cline.
5. Confirm the MCP server is active.

Securing API Keys:
Tokens are kept secure via the env field in your configuration.

Windsurf

No setup instructions provided for Windsurf.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "logfire": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change "logfire" to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Roots Support: ⛔ (Not documented)

Sampling Support: ⛔ (Not documented)

Based on the above, Logfire MCP Server is a focused, production-quality MCP server for observability, but lacks documentation for prompt templates, resources, roots, or sampling support. It excels at exposing a small set of high-value tools for telemetry and debugging. Final rating: 6/10 — excellent for its use case, but not a full-featured MCP reference implementation.

MCP Score