Tideways MCP Server

MCP server for Tideways performance monitoring integration with AI assistants

Local serverstdioTypeScript

What is the Tideways MCP server?

MCP server for Tideways performance monitoring integration with AI assistants. That is what the tideways mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

A Model Context Protocol (MCP) server that enables AI assistants to query Tideways performance monitoring data and provide conversational performance insights for PHP applications.

  • Conversational Performance Insights — Get performance data in natural language format optimized for AI assistants
  • AI Assistant Integration — Works with Claude Desktop, Cursor, Claude Code, and other MCP-compatible tools
  • Real-time Performance Metrics — Query current performance data with configurable rate limiting
  • Trace Analysis — List and filter traces with layer breakdown, bottleneck detection, and response time analysis
  • Issue Analysis — Retrieve and analyze errors, exceptions, and performance issues
  • Robust Error Handling — Comprehensive error handling with user-friendly messages

The tools it exposes

The server publishes 6 tools. What each one is for:

  • get_performance_metrics — Retrieve aggregate performance metrics and system-wide statistics
  • get_performance_summary — Retrieve time-series performance summary data in 15-minute intervals for trend analysis
  • get_issues — Retrieve and analyze recent errors, exceptions, and performance issues
  • get_traces — Analyze individual trace samples for detailed bottleneck identification and performance debugging
  • get_historical_data — Retrieve historical performance data for specific dates with configurable granularity
  • Building — The Building tool exposed by this server

What it needs from you

Configuration is passed through the environment: TIDEWAYS_TOKEN, TIDEWAYS_ORG, TIDEWAYS_PROJECT, LOG_LEVEL, TIDEWAYS_BASE_URL, YOUR_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  • Tideways account with a valid API token - API token with appropriate scopes (metrics, issues, traces) - see API documentation - Access to a Tideways organization and project

Getting it running

tideways-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

How it compares

This sits in the monitoring and observability group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Tideways's toolset — get_performance_metrics, get_performance_summary, get_issues and 3 more — is a fair guide to whether it matches your workflow. It is maintained by 5hahil; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
get_performance_metricsRetrieve aggregate performance metrics and system-wide statistics.
get_performance_summaryRetrieve time-series performance summary data in 15-minute intervals for trend analysis.
get_issuesRetrieve and analyze recent errors, exceptions, and performance issues.
get_tracesAnalyze individual trace samples for detailed bottleneck identification and performance debugging.
get_historical_dataRetrieve historical performance data for specific dates with configurable granularity.
BuildingThe Building tool exposed by this server.

How to install the Tideways MCP server

{
  "mcpServers": {
    "tideways": {
      "command": "npx",
      "args": ["tideways-mcp"],
      "env": {
        "TIDEWAYS_TOKEN": "your_token",
        "TIDEWAYS_ORG": "your_org",
        "TIDEWAYS_PROJECT": "your_project"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Tideways account with a valid API token - API token with appropriate scopes (metrics, issues, traces) - see API documentation - Access to a Tideways organization and project
VariableDescriptionRequired
TIDEWAYS_TOKENCredential the server authenticates with.Yes
TIDEWAYS_ORGConfiguration value read at startup.Optional
TIDEWAYS_PROJECTConfiguration value read at startup.Optional
LOG_LEVELConfiguration value read at startup.Optional
TIDEWAYS_BASE_URLEndpoint or connection string the server talks to.Yes
YOUR_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Tideways to get performance metrics.
  • Use Tideways to get performance summary.
  • Use Tideways to get issues.

Frequently asked questions

It connects Tideways to MCP-compatible AI assistants such as Claude and Cursor, exposing 6 tools (get_performance_metrics, get_performance_summary, get_issues, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Tideways directly.