PHPRay MCP server

• Registry namedev.phpray/phprayverified in the MCP registry

The registry name sits under phpray.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-26
• Tools10
• Server calls itselfphpray
• Server version0.15.7
• Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 184 ms.

• Its tools do every use case we checked: find which WordPress plugin slows a page; trace SQL and HTTP time within one slow request.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP score87 of 100answers 100 · does the job 100 · definitions 83 · context 100 · use 0 · connects 100
• What an agent can do with it2 of 2 use cases
• Answered100% of days8 of 8 daily checks
• Median first answer574 ms
• Space in an agent's context≈ 1,150 tokensthe definitions of all its tools (10), which an agent carries on every turn
• Tool definitionsB · 83 of 100
• Typed results0 of 10 toolsdeclared outputSchema: results come typed, read once

• Not saying whether it only reads or can destroy: 10 of 10

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• phpray_sites

  List 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_overview

  Headline 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.

• phpray_slow_pages

  The slowest URLs on a site, with request counts and p95, from the request timeseries. Answers "which page is slow".

• phpray_slow_queries

  SQL fingerprints ordered by time spent, with call counts and the caller when known. Literals are already masked. Answers "which query is slow".

• phpray_components

  Time 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.

• phpray_errors

  Requests 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.

• phpray_traces

  Recent requests for a site. Filter with min_ms and status to find the bad ones, then pass an id to phpray_trace.

• phpray_trace

  One 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.

• phpray_compare

  Two 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.

• phpray_alerts

  Alerts currently firing across every site this token can see, worst overrun first.