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.

io.github.mgriffen/tapsite

NPM · TAPSITE · SCANNED SEP 20

MCP server for web inspection, design system extraction, and accessibility audits

Available components

0 this week 82 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 97 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 154 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability68
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 2338 tokens (~54/item across 43 items; 43 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
  • Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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 43 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 43 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
Install

How do I install the io.github.mgriffen/tapsite MCP server?

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

npm · tapsite

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

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 16 Sept 26 0
    • Stability: 0.97 → pass security
  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 −3
    • Security disclosure: unverified → pass functional
    • Stability: pass → 0.80 functional
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 20 Sept 2026 · Analysed npm/tapsite@4.0.1

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 97 packages
Packages resolved 97
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 43 exposed · ~2,338 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
tapsite_audit ~72

Pre-launch quality audit with scorecard — runs a11y, contrast, perf, metadata (SEO), dark mode, and forms. Returns pass/fail per category with an overall score out of 100.

NameTypeReqDescription
standardstringWCAG standard
urlstringyesURL to audit

No output schema declared.

No examples provided.

tapsite_capture_network ~88

Capture network traffic for a duration. Filters static assets by default.

NameTypeReqDescription
durationnumberSeconds to capture (1-60)
filterMethodstringFilter: HTTP method
filterUrlstringFilter: URL contains string
includeStaticbooleanInclude images/CSS/fonts
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_close ~14

Close the browser session.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

tapsite_crawl ~103

BFS crawl with extraction per page. Writes to output/crawl-{ts}/.

NameTypeReqDescription
extractarrayExtractions per page
filterPathstringPath prefix filter (e.g. '/blog/')
maxDepthnumberMax link depth (0-10)
maxPagesnumberMax pages (1-100)
sameDomainbooleanSame domain only
urlstringyesStart URL

No output schema declared.

No examples provided.

tapsite_designsystem ~74

Design system extraction — runs colors, fonts, spacing, shadows, CSS vars, breakpoints, animations, icons, and components. Exports W3C design-tokens.json, design-tokens.css, and raw-data.json to output/design-system-{ts}/.

NameTypeReqDescription
urlstringyesURL to extract from

No output schema declared.

No examples provided.

tapsite_diff_pages ~158

Compare two URLs (cross-site) or the same URL over time (temporal). Runs real extractors — colors, fonts, spacing, a11y, perf, metadata, components, breakpoints — and produces a structured diff with regressions/improvements highlighted. Omit url2 for temporal mode (compares against last saved snapshot).

NameTypeReqDescription
extractorsarrayWhich extractors to run (default: all core). Options: colors, fonts, spacing, components, breakpoints, a11y, perf, metadata, contrast
url1stringyesFirst URL / baseline (or sole URL for temporal mode)
url2stringSecond URL to compare against url1 (omit for temporal diff)

No output schema declared.

No examples provided.

tapsite_download_images ~89

Download images to disk. Uses session cookies for auth assets.

NameTypeReqDescription
filterstringFilter: src contains string
formatsarrayExtensions filter (e.g. ['png','jpg'])
limitnumberMax images (1-200)
minWidthnumberMin width in px
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_export ~33

Export URLs as Markdown + HTML report + JSON + CSV + screenshots.

NameTypeReqDescription
urlsarrayyesURLs to export

No output schema declared.

No examples provided.

tapsite_export_design_report ~47

Full design system report: HTML + W3C tokens JSON + CSS vars.

NameTypeReqDescription
includearraySections to include
urlstringyesURL to analyze

No output schema declared.

No examples provided.

tapsite_extract_a11y ~53

Accessibility audit with score (0-100) and issues by severity.

NameTypeReqDescription
standardstringWCAG standard (aa or aaa)
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_animations ~35

Extract CSS animations, transitions, and detect animation libraries.

NameTypeReqDescription
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_api_schema ~59

Infer API schemas from captured network traffic.

NameTypeReqDescription
durationnumberSeconds to capture (1-60)
filterUrlstringFilter: URL contains string
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_breakpoints ~39

Extract CSS breakpoints and detect framework (Tailwind/Bootstrap/MUI).

NameTypeReqDescription
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_colors ~39

Extract color palette sorted by frequency.

NameTypeReqDescription
limitnumberMax colors
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_components ~44

Detect repeated UI component patterns with instance counts.

NameTypeReqDescription
minOccurrencesnumberMin occurrences to qualify
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_content ~57

Extract main content as clean markdown, stripping chrome.

NameTypeReqDescription
includeImagesbooleanInclude images in output
selectorstringCSS selector to scope extraction
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_contrast ~63

WCAG contrast ratio audit between text and background color pairs.

NameTypeReqDescription
sampleSizenumberMax text elements to check
standardstringWCAG standard (aa or aaa)
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_css_vars ~45

Extract CSS custom properties, categorized by type.

NameTypeReqDescription
includeAllbooleanAlso scan inline styles
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_darkmode ~50

Detect dark mode support. Optionally capture dark palette.

NameTypeReqDescription
activateDarkbooleanEmulate dark mode and capture palette
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_favicon ~47

Extract favicon and icon references. Optional download.

NameTypeReqDescription
downloadbooleanDownload to output/assets/favicons/
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_fonts ~34

Extract fonts: families, sizes, weights, sources.

NameTypeReqDescription
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_forms ~35

Extract forms: fields, validation, actions, hidden fields.

NameTypeReqDescription
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_icons ~42

Detect icon font libraries and extract icon usage (Font Awesome, Material, Bootstrap Icons, etc.).

NameTypeReqDescription
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_images ~59

Extract all images with src, dimensions, alt, format.

NameTypeReqDescription
filterstringFilter: src contains string
minWidthnumberMin width in px
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_layout ~45

Extract layout tree: flex/grid/block containers with properties.

NameTypeReqDescription
maxDepthnumberMax tree depth
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_links ~44

Extract all links with text and href.

NameTypeReqDescription
filterstringFilter: href contains this string
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_metadata ~39

Extract metadata: OG, Twitter Cards, JSON-LD, RSS, canonical.

NameTypeReqDescription
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_perf ~35

Performance metrics: Web Vitals, resource sizes, timing.

NameTypeReqDescription
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_shadows ~47

Extract box-shadow and text-shadow patterns as design tokens.

NameTypeReqDescription
sampleSizenumberMax elements to sample
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_spacing ~48

Extract spacing scale: margins, padding, gaps, radii.

NameTypeReqDescription
sampleSizenumberMax elements to sample
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_stack ~38

Detect tech stack: frameworks, libraries, CMS, analytics, CDNs.

NameTypeReqDescription
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_svgs ~68

Extract SVGs: inline markup, external URLs, icon/illustration classification.

NameTypeReqDescription
downloadbooleanDownload to output/assets/svgs/
limitnumberMax SVGs (1-200)
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_extract_table ~51

Extract table data as structured rows.

NameTypeReqDescription
limitnumberMax rows
minColumnsnumberMin columns per row
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_harvest ~85

Migration asset inventory — crawls up to maxPages pages and extracts content, images, SVGs, forms, fonts, and links per page. Returns per-page counts and a link map. Output written to output/harvest-{ts}/.

NameTypeReqDescription
maxPagesnumberMax pages to crawl (1-50)
urlstringyesStart URL

No output schema declared.

No examples provided.

tapsite_inspect ~51

Navigate to URL and/or inspect page DOM with numbered interactive elements. Optional screenshot.

NameTypeReqDescription
screenshotbooleanInclude screenshot
urlstringURL to navigate to (omit for current page)

No output schema declared.

No examples provided.

tapsite_interact ~61

Click, fill, select, check, or hover an indexed element. Returns updated DOM.

NameTypeReqDescription
actionstringyesAction type
indexnumberyesElement index from inspect/navigate
valuestringValue for fill/select

No output schema declared.

No examples provided.

tapsite_login ~78

Auto-login with credentials. Session persists across calls.

NameTypeReqDescription
passwordstringyesPassword
passwordSelectorstringPassword field selector
submitSelectorstringSubmit button selector
urlstringyesLogin page URL
usernamestringyesUsername
usernameSelectorstringUsername field selector

No output schema declared.

No examples provided.

tapsite_login_check ~25

Verify auth state after manual login. Returns title, URL, content preview.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

tapsite_login_manual ~36

Open headed browser for manual login (MFA). Call login_check when done.

NameTypeReqDescription
urlstringyesLogin page URL

No output schema declared.

No examples provided.

tapsite_run_js ~40

Run JS in page context. Large results (>2KB) write to disk.

NameTypeReqDescription
scriptstringyesJS expression (must return a value)

No output schema declared.

No examples provided.

tapsite_screenshot ~57

Screenshot the page. Optional element highlighting with numbered badges.

NameTypeReqDescription
fullPagebooleanFull scrollable page
highlightbooleanOverlay numbered element badges
urlstringURL (omit for current page)

No output schema declared.

No examples provided.

tapsite_scroll ~43

Scroll page or scroll an element into view.

NameTypeReqDescription
directionstringDirection (ignored if index set)
indexnumberElement index to scroll to

No output schema declared.

No examples provided.

tapsite_teardown ~68

Competitive design teardown — runs colors, fonts, CSS vars, spacing, shadows, components, breakpoints, animations, icons, stack detection, perf, a11y, contrast, and dark mode in one call. Returns a combined summary.

NameTypeReqDescription
urlstringyesURL to analyze

No output schema declared.

No examples provided.

Common questions

What is the io.github.mgriffen/tapsite MCP server?

io.github.mgriffen/tapsite is an MCP server listed in the public MCP registry as io.github.mgriffen/tapsite. MCP server for web inspection, design system extraction, and accessibility audits. This page covers its npm package (tapsite).

Is the io.github.mgriffen/tapsite MCP server safe to use?

io.github.mgriffen/tapsite scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 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 io.github.mgriffen/tapsite MCP server expose?

io.github.mgriffen/tapsite exposes 43 tools: tapsite_login, tapsite_login_manual, tapsite_login_check, tapsite_inspect, tapsite_screenshot, and 38 more. Their descriptions and schemas cost roughly 2,338 tokens of context every time the server is loaded.

Is the io.github.mgriffen/tapsite MCP server still maintained?

io.github.mgriffen/tapsite is still listed as active in the MCP registry. We last reached this channel on 20 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 io.github.mgriffen/tapsite MCP server under?

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