Index / MCP servers / Phpray

Phpray MCP server

Phpray is a remote MCP server that gives an AI agent 10 tools, among them phpray_alerts, phpray_compare, phpray_components. It answers at https://phpray.dev/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 3 of 4 times since 23 September 2026; the last check, on 7 November 2026, succeeded.

Status
Answering
Tools
10
Official
yes, served from phpray.dev
Reliability
3 of 4 checks
Response time
306 ms
Transport
streamable HTTP
Last checked
7 November 2026

Ask an agent why a PHP site is slow: every request with its SQL, HTTP calls, errors and N+1.

Description as the publisher wrote it.

The 10 tools Phpray offers

ToolWhat it does
phpray_alertsAlerts currently firing across every site this token can see, worst overrun first.
phpray_compareTwo time ranges for one site side by side. Use it to check whether a deployment, a plugin update or a configuration change made things better or worse.
Inputs: from_a, from_b, site_id, to_a, to_b
phpray_componentsTime attributed to each plugin, theme or vendor package on profiled requests. Answers "which plugin is slowing the site down". Empty when function profiling is off.
Inputs: limit, site_id, window_minutes
phpray_errorsRequests that failed on a site: PHP errors and warnings with file and line where PHP raised one, plus 5xx responses that carry no PHP error. Pass an id to phpray_trace to see what one of them did.
Inputs: limit, site_id, window_minutes
phpray_overviewHeadline numbers for one site over a time window: requests, errors, p50/p95/p99 latency, database share and N+1 count. Use this before digging into anything else.
Inputs: site_id, window_minutes
phpray_sitesList the PHP sites this token can see, with requests, p95 latency and error rate. Start here: every other tool needs a site_id from this list.
phpray_slow_pagesThe slowest URLs on a site, with request counts and p95, from the request timeseries. Answers "which page is slow".
Inputs: limit, site_id, window_minutes
phpray_slow_queriesSQL fingerprints ordered by time spent, with call counts and the caller when known. Literals are already masked. Answers "which query is slow".
Inputs: limit, site_id, window_minutes
phpray_traceOne request in full: wall time split into PHP, database and outbound HTTP, every query, every external call, errors, and the component breakdown when the request was profiled.
Inputs: trace_id
phpray_tracesRecent requests for a site. Filter with min_ms and status to find the bad ones, then pass an id to phpray_trace.
Inputs: limit, min_ms, site_id, status, window_minutes

Add Phpray to your AI client

Every block below points at https://phpray.dev/mcp. Pick your client and copy.

Claude Code: one command in your terminal
claude mcp add --transport http phpray https://phpray.dev/mcp
Claude Desktop: claude_desktop_config.json
{
  "mcpServers": {
    "phpray": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://phpray.dev/mcp"]
    }
  }
}
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project
{
  "mcpServers": {
    "phpray": {
      "url": "https://phpray.dev/mcp"
    }
  }
}
VS Code and GitHub Copilot: .vscode/mcp.json
{
  "servers": {
    "phpray": {
      "type": "http",
      "url": "https://phpray.dev/mcp"
    }
  }
}
Zed: Zed settings.json
{
  "context_servers": {
    "phpray": {
      "url": "https://phpray.dev/mcp"
    }
  }
}
Windsurf: ~/.codeium/mcp_config.json
{
  "mcpServers": {
    "phpray": {
      "serverUrl": "https://phpray.dev/mcp"
    }
  }
}
JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON
{
  "mcpServers": {
    "phpray": {
      "url": "https://phpray.dev/mcp"
    }
  }
}
Continue: .continue/mcpServers/neuronto.yaml
name: Phpray
version: 0.0.1
schema: v1
mcpServers:
  - name: Phpray
    type: streamable-http
    url: https://phpray.dev/mcp
Gemini CLI: ~/.gemini/settings.json
{
  "mcpServers": {
    "phpray": {
      "httpUrl": "https://phpray.dev/mcp"
    }
  }
}
Codex CLI: MCP server config
{
  "mcpServers": {
    "phpray": {
      "type": "http",
      "url": "https://phpray.dev/mcp"
    }
  }
}
Warp: MCP servers, + Add, paste JSON
{
  "mcpServers": {
    "phpray": {
      "url": "https://phpray.dev/mcp"
    }
  }
}
Goose: a one-click extension link
goose://extension?url=https%3A%2F%2Fphpray.dev%2Fmcp&type=streamable_http&id=phpray&name=Phpray

Is Phpray up right now?

It answered our last check on 7 November 2026 in 306 ms. Over 4 checks since 23 September 2026 it answered 3. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to Phpray

Questions about Phpray

Is there an official Phpray MCP server?

Yes. It is published by phpray.dev and served from phpray.dev, the vendor's own domain: https://phpray.dev/mcp.

How many tools does Phpray have?

10, as returned by the server's own tools/list on 13 November 2026: phpray_alerts, phpray_compare, phpray_components, phpray_errors, phpray_overview, phpray_sites, phpray_slow_pages, phpray_slow_queries, and 2 more.

Is Phpray down?

It answered our last check on 7 November 2026 in 306 ms. Over 4 checks since 23 September 2026 it answered 3.

How do I add Phpray to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://phpray.dev/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does Phpray need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: dev.phpray. Endpoint host: phpray.dev. ARD identifier: urn:air:dev.phpray:mcp:phpray. First indexed 22 September 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.