Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

pxtree

NPM · PXTREE · SCANNED SEP 26

Measures how a webpage actually renders and prints it as compact text for AI coding agents.

Available components

67 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability57
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 804 tokens (~402/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

Install

How do I install the pxtree MCP server?

pxtree runs locally as an npm package, launched with npx -y pxtree. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · pxtree

# add to Claude Code
claude mcp add alabsi91-pxtree -- npx -y pxtree
// .cursor/mcp.json
{
  "mcpServers": {
    "alabsi91-pxtree": {
      "command": "npx",
      "args": [
        "-y",
        "pxtree"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "alabsi91-pxtree": {
      "command": "npx",
      "args": [
        "-y",
        "pxtree"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add alabsi91-pxtree -- npx -y pxtree
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "alabsi91-pxtree": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "pxtree"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add alabsi91-pxtree --command npx --arg -y --arg pxtree
# ~/.hermes/config.yaml
mcp_servers:
  alabsi91-pxtree:
    command: "npx"
    args: ["-y", "pxtree"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "alabsi91-pxtree": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "pxtree"
      ]
    }
  }
}
# add to Vellum
assistant mcp add alabsi91-pxtree -t stdio -c npx -a -y pxtree
// mcp.json
{
  "mcpServers": {
    "alabsi91-pxtree": {
      "command": "npx",
      "args": [
        "-y",
        "pxtree"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 24 Sept 26 67

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 26 Sept 2026 · Analysed npm/pxtree@0.1.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 96 packages
Packages resolved 96
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 2 exposed · ~762 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
measure ~731

Measures how a webpage renders in headless Chromium and returns compact text: a facts line, changes since the last run, a findings summary, then an indented tree, one line per element. Findings are measurements that passed a threshold, never verdicts. Parameters: target (URL, host or HTML file path), viewports, schemes, scroll, element, children, colors, wait, script (Playwright page code), screenshot, timeout, diff, diffKey, report (tree, findings, summary, changes or none), aria (names, roles, states). One call returns the report, aria tree and screenshot for every viewport, scheme and scroll stop. Never split a question into parallel calls: one browser page, calls run one at a time. Call read_me_first once per session before the first measure to learn the tags and findings.

NameTypeReqDescription
ariaboolean–A boolean: add Playwright's aria snapshot of the page, or of each element match, after the report
childrenboolean–A boolean. With element: include what is inside the matches. Default true
colorsboolean–A boolean: print hex colors in [text] and [renders]
diffboolean–A boolean: compare with the previous run of the same target and settings. Default true
diffKeystring–A name string that replaces script and wait in the since-last-run key, to compare a scripted run with a plain run that used the same name
elementstring–A CSS selector string: print only matching elements and their ancestor lines
maxCharsnumber–A number: the longest report in characters. Past it the tree is cut at a line; facts, since last run and summary stay. Default 80000
reportstring–One of "tree", "findings", "summary", "changes", "none". tree: everything. findings: only lines with findings and their ancestors. summary: no tree. changes: facts line and since last run. none: fact…
schemesarray–An array of "light" and "dark", the prefers-color-scheme per run. Default ["light"]
screenshotboolean–A boolean: save a PNG per run under the OS temp directory and return its path
scriptstring–A string: the body of async (page) => {}, or a whole function like async (page) => {}, run with the Playwright page before measuring. It is trusted code that runs as Node in the server process with i…
scroll––A stop or an array of stops: a number or digit string is a window y offset, "end" is the bottom, anything else is a CSS selector to scroll to the top. An array measures each stop in turn, one run per…
targetstringyesA string: URL, host like localhost:5173, or HTML file path under the working directory
timeoutnumber–A number of milliseconds to reach DOMContentLoaded. The script, a wait, reveal, settle and measuring each get this long again. Default 30000
viewportsarray–An array of { width, height } with integer numbers, one run each. Default [{ width: 1280, height: 800 }]
wait––After the script: a number or digit string of milliseconds to sleep, at most timeout, or a CSS selector string to wait up to timeout for

No output schema declared.

No examples provided.

read_me_first ~31

Read once per session before the first measure. How to use pxtree and how to read its output.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Common questions

What is the pxtree MCP server?

pxtree is an MCP server listed in the public MCP registry as io.github.alabsi91/pxtree. Measures how a webpage actually renders and prints it as compact text for AI coding agents. This page covers its npm package (pxtree).

Is the pxtree MCP server safe to use?

pxtree scores 67 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 26 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the pxtree MCP server expose?

pxtree exposes 2 tools: measure, read_me_first. Their descriptions and schemas cost roughly 762 tokens of context every time the server is loaded.

Is the pxtree MCP server still maintained?

pxtree is still listed as active in the MCP registry. We last reached this channel on 26 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the pxtree MCP server under?

pxtree declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.