pagesnap-mcp
pagesnap-mcp
MCP-Server, der bestehende PageSnap-Session-Pakete kapselt, damit ein LLM Sessions auflisten, Locators lesen und sie Playwright, Selenium oder Cypress zuordnen kann.
Dies ist KEIN Erfassungstool. Es öffnet keinen Browser, scannt keine URLs automatisch und ruft keine Browser ab. Playwright ist keine Abhängigkeit.
Die Erfassung erfolgt in pagesnap-playwright oder pagesnap-selenium. Richten Sie diesen Server auf einen übergeordneten Ordner mit Session-Paketen aus (flow.md plus yaml plus optional PROMPT.md).
Ausführung
npm install
npm run build
node dist/index.jsDer Prozess spricht MCP über stdio und wartet auf stdin. Er wirkt in einem Terminal eingefroren; das ist erwartet. Beenden Sie ihn mit Ctrl+C. Optionale Umgebungsvariable: PAGESNAP_SESSIONS_DIR (Standard ./sessions) ist der übergeordnete Ordner der PageSnap-Session-Ordner.
Related MCP server: Browser MCP Server
Cursor-MCP-Konfiguration
Beispiel .cursor/mcp.json. Richten Sie PAGESNAP_SESSIONS_DIR auf ein übergeordnetes PageSnap-Session-Verzeichnis aus, z. B. playwright-ts-framework/snapshots:
{
"mcpServers": {
"pagesnap": {
"command": "node",
"args": [
"/absolute/path/to/pagesnap-mcp/dist/index.js"
],
"env": {
"PAGESNAP_SESSIONS_DIR": "/absolute/path/to/playwright-ts-framework/snapshots"
}
}
}
}Dieser Server liest nur Pakete, die bereits auf der Festplatte liegen. Er ist kein Erfassungstool.
Werkzeuge
Token-effizient: list_sessions und read_session geben zuerst Schlüssel und Zusammenfassungen zurück. Die Inhalte der YAML-Dateien werden nicht ausgegeben.
list_sessions: keine Argumente. Sessions aus PAGESNAP_SESSIONS_DIR.
read_session: { session }. flow.md, YAML-Dateinamen, geparste Steuerelemente (max. 200).
map_locator: { by, value, name?, framework? }. snippet, score, stability. framework: playwright|selenium|cypress (Standard playwright).
get_prompt: { session, framework? }. PROMPT.md falls vorhanden, andernfalls ein erzeugter Prompt.
Locators
YAML-Werte: testid, role, label, id, name, placeholder, linkText, css, xpath. Scores entsprechen PageSnap: testid 98, role 95, label/id 90, name 88, placeholder 85, linkText 75, css 60, xpath 40. Playwright testid wird immer auf page.getByTestBy(...) abgebildet. Sauce Demo verwendet data-test über Playwright testIdAttribute; geben Sie dennoch getByTestBy aus. Generische data-testid-Knoten ohne Rolle werden weiterhin auf getBytestGetBy abgebildet, niemals auf getByRole('generic').
Tests
npx vitest runLizenz
MIT
Available Tools
4 toolsget_promptA
Return PROMPT.md for a session if present; otherwise synthesize a test-generation prompt from flow.md and ranked locators.
Inputs: session (required), framework.
list_sessionsA
List PageSnap session packs under PAGESNAP_SESSIONS_DIR (default ./sessions). Returns a summary only: name, path, mtime, goal, stepCount. Does not capture or open a browser.
Inputs: no named parameters.
map_locatorA
Map a PageSnap YAML locator {by, value} to a Playwright, Selenium, or Cypress snippet with score and stability. Sauce Demo data-test ids still emit getByTestId (configure testIdAttribute in Playwright). Never maps testid to getByRole('generic').
Inputs: by (required), value (required), name, framework.
read_sessionA
Read one PageSnap session: flow.md, YAML file names, and parsed controls (cap 200). Token-efficient: keys/summary first; does not dump YAML file bodies.
Inputs: session (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool maps to a clearly distinct concern: listing sessions, reading session details, translating locators, and generating prompts. There is no overlap that would cause an agent to select the wrong tool.
All tool names follow a consistent verb_noun snake_case pattern: list_sessions, read_session, map_locator, get_prompt. This makes the tool set predictable and easy to navigate.
Four tools is a tight, focused scope. Each tool earns its place and supports a distinct step in the PageSnap session inspection workflow without redundancy.
The read-and-analyze workflow is well covered: list, read, map, and prompt. A minor gap is the lack of session creation or mutation tools, but the descriptions frame this as a read-only inspection tool, so the gaps are acceptable.
Maintenance
Related MCP Connectors
Give agents eyes on any web page: structured context, and changes explained in plain language.
Undetectable cloud browser sessions for AI agents and scrapers. Navigate, extract, click, captcha.
Give AI agents a real cloud Chrome: open sessions, navigate, read pages, click, type and screenshot.
Captured web interfaces, screenshots, flows and structured evidence for AI coding agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides browser automation capabilities for LLMs using Playwright, leveraging structured accessibility snapshots to interact with web pages without needing vision models. It enables tasks like web navigation, data extraction, and automated testing through a lightweight and deterministic toolset.8 npmApache 2.0
- AlicenseAqualityDmaintenanceEnables AI agents to understand web page structure and content through structured data extraction and element discovery using Playwright, eliminating the need for screenshots.46 npmMIT
- AlicenseAqualityBmaintenanceDrives a real Chromium browser to extract a page's DOM into compact Semantic JSON with Playwright-native locators, enabling AI agents to generate consistent, accurate Playwright tests.1335 npm3MIT
- AlicenseNot gradedqualityDmaintenanceEnables LLMs to interact with web pages through structured accessibility snapshots using Playwright, providing fast and lightweight browser automation without needing vision models.Apache 2.0