Our MCP server

The Flare MCP server allows you to integrate Flare's error tracking and performance monitoring capabilities directly into your AI-powered development workflows. Use it with AI assistants like Claude to automatically monitor, analyze, and resolve application errors, and investigate performance issues.

What is MCP?

MCP (Model Context Protocol) is an open protocol that enables AI assistants to securely connect with external data sources and tools. By using the Flare MCP server, your AI assistant gains direct access to your error tracking and performance monitoring data and can perform actions in Flare on your behalf.

Key features

With the Flare MCP server, you can ask your AI assistant to:

• "Show me the latest errors from my project"
• "Fix the error regarding the PHP syntax error in myfile.php"
• "Mark the error as resolved in Flare"
• "Fix error ERROR-ID-HERE and mark the error as resolved"
• "Show me all slow routes in my app"
• "Show me the monitoring summary for my project"
• "List the slowest database queries from the last 7 days"
• "Show me traces for this route aggregation"
• "Create a note in Flare with the results of your investigation about this error"

Getting started

Step 1: Create an API token

First, create an API token in your Flare account settings. This token will authenticate your AI assistant with Flare.

Step 2: Configure your AI assistant

Choose your AI assistant below and follow the specific configuration steps.

Step 3: Add project hints

To help your AI assistant use the Flare MCP server effectively, provide it with context about your projects. For example:

"When a user asks to show or investigate an error, use the Flare MCP tool to get data. The project name in Flare is INSERT-YOUR-PROJECT-NAME-HERE."

Installation in Claude Code

Configure the Flare MCP server for Claude Code:

claude mcp add --transport http flare https://flareapp.io/mcp \
--header "Authorization: Bearer <INSERT-YOUR-TOKEN-HERE>"

Optionally, verify that the server was added successfully:

claude mcp get flare

Add the project hint to your CLAUDE.md file:

"When a user asks to show or investigate an error, use the Flare MCP tool to get data. The project name in Flare is INSERT-YOUR-PROJECT-NAME-HERE."

Installation in Junie

Configure the Flare MCP server for JetBrains' Junie AI assistant (available in PhpStorm and other JetBrains IDEs).

Create or edit the configuration file at ~/.junie/mcp/mcp.json:

{
  "mcpServers": {
    "flare": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://flareapp.io/mcp",
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer <YOUR-API-TOKEN>"
      }
    }
  }
}

Alternative: Agent skill

If you're looking for a simpler setup that works across more AI coding tools, check out the Flare agent skill. It teaches any compatible AI coding agent to use the Flare CLI — no per-client server configuration required.

Beta status

This functionality is currently in beta. If you have any feedback or questions, please reach out to us at [email protected].

Available commands

Once configured, your AI assistant can:

• List projects: View all projects associated with your Flare account
• Show errors: Display recent errors from a specific project
• View error details: Get full information about a specific error including stack traces and context
• Resolve errors: Mark errors as resolved directly from your AI conversation
• Search errors: Find errors matching specific criteria
• Create notes: Add investigation notes to errors for team collaboration
• Monitor performance: View monitoring summaries, list aggregations by type (routes, queries, jobs, commands), inspect detailed metrics and trends, and browse traces for any aggregation

Security

The Flare MCP server uses your API token for authentication. This token provides the same access level as your user account, so keep it secure and never share it publicly. You can revoke tokens at any time from your Flare account settings.