Skip to main content
Glama
298,188 tools. Last updated 2026-07-14 11:30

"playwright" matching MCP tools:

  • Use this when you need to LOOK at a kernelCAD model — render its script to deterministic PNG views for visual self-check (the visual half of the evaluate → render → inspect → fix loop), with NO studio or dev server required. Pass { code } (inline source) or { file } (a .kcad.ts path), exactly one. Renders the canonical engineering views (front, right, top, iso — pass { views } for a subset, e.g. ["iso"] for fastest iteration) plus an optional { pose: "<az>,<el>" } arbitrary camera angle (degrees; az=0,el=0 is front, +az rotates CCW around +Z, +el lifts the camera). NO STUDIO / DEV-SERVER REQUIRED: a prebuilt static player (dist/headless-player) is served from an ephemeral local port automatically; a running studio dev server is used as fallback, and { base_url } forces one. The only environment dependency is playwright chromium (npx playwright install chromium). Pass { focus } or { hide } (arrays of feature ids or assembly part names, mutually exclusive) to isolate parts — same semantics as `kernelcad render --focus/--hide`. PNGs are written to { out_dir } (default: a fresh temp session directory) and returned as absolute paths with per-view camera descriptions (kernelCAD is Z-up). Mechanism truth runs first, same protocol as `kernelcad render`: a broken mechanism still renders but every tile is watermarked MECHANISM BROKEN (KERNELCAD_RENDER_STRICT=1 refuses instead); read { mechanism, mechanism_failure_codes }. The probe runs full BREP interference sweeps and can dominate latency on large assemblies — pass { no_mechanism_check: true } for fast iteration (the preview then reports mechanism: "unverified"; ignored under strict mode). Returns { ok, images: [{ name, path, description }], out_dir, bounds, mechanism, render_source, render_ms, diagnostics }. PATHS ARE LOCAL to the machine running the MCP server — local stdio clients read them directly; hosted/remote clients should use open_in_studio instead.
    Connector
  • Give any agent eyes. Pass any public URL → get back a structured intelligence report: page title, meta tags, all headings (H1–H6), full body text, every form mapped with fields and input types, all links, images, and pattern detection (prices, emails, dates). Anomaly flags included: JS-heavy SPA, Cloudflare challenge, CAPTCHA, access restrictions. One tool call turns a blind agent into one that can observe anything on the internet. No Playwright config. No browser infra to spin up. x711 is the browser — agent never touches it. Returns: { title, meta, headings, body_text, links, forms, images, detected: {prices, emails, dates}, anomalies, note }. Cost: $0.03. Pair with x711_agent_act to complete the full browser loop.
    Connector
  • Give any agent eyes. Pass any public URL → get back a structured intelligence report: page title, meta tags, all headings (H1–H6), full body text, every form mapped with fields and input types, all links, images, and pattern detection (prices, emails, dates). Anomaly flags included: JS-heavy SPA, Cloudflare challenge, CAPTCHA, access restrictions. One tool call turns a blind agent into one that can observe anything on the internet. No Playwright config. No browser infra to spin up. x711 is the browser — agent never touches it. Returns: { title, meta, headings, body_text, links, forms, images, detected: {prices, emails, dates}, anomalies, note }. Cost: $0.03. Pair with x711_agent_act to complete the full browser loop.
    Connector
  • Give any agent hands. Pass a URL + natural-language instruction → x711 executes it: fills and submits forms, follows links, extracts structured data (tables, lists, prices). No Playwright. No Puppeteer. No browser setup. Together with x711_agent_see this is a full browser in two tool calls — agents that can see + act can navigate the entire internet autonomously. Instruction examples: 'fill the email field with user@example.com and submit', 'extract all product prices', 'follow the login link and return the page'. Returns: { action_performed, result, page_status }. JS SPA warning included if detected. Cost: $0.05. Requires API key.
    Connector
  • Restore an expired integration session by capturing the LIVE auth of an open browser page — works for COOKIE sessions (browser_identity) AND TOKEN/HEADER sessions (bearer / api_key / custom_headers, e.g. Devise access-token/client/uid). First call browser_open(url, identity_name) for the integration's site (the page must be logged in AND have called its API), then pass that `page_id` here with `integration_id` or `base_url`. For cookie sessions it captures the full storage_state (incl httpOnly cookies page JS can't read) into the bound identity; for token sessions it captures the auth headers the page sends to the API host and binds them. Re-connects the integration. The captured secret never leaves the server (returns counts only). Generic — any site, any auth scheme, no local Playwright.
    Connector
  • Give any agent hands. Pass a URL + natural-language instruction → x711 executes it: fills and submits forms, follows links, extracts structured data (tables, lists, prices). No Playwright. No Puppeteer. No browser setup. Together with x711_agent_see this is a full browser in two tool calls — agents that can see + act can navigate the entire internet autonomously. Instruction examples: 'fill the email field with user@example.com and submit', 'extract all product prices', 'follow the login link and return the page'. Returns: { action_performed, result, page_status }. JS SPA warning included if detected. Cost: $0.05. Requires API key.
    Connector

Matching MCP Servers

  • F
    license
    B
    quality
    D
    maintenance
    Playwright MCP server enables AI-driven Playwright test generation by allowing interaction with web pages and element inspection. Integrated with IDEs like Cursor, it provides real-time context to enhance test accuracy and efficiency.
    Last updated
    5
    11,810
    32

Matching MCP Connectors

  • Restore an expired integration session by capturing the LIVE auth of an open browser page — works for COOKIE sessions (browser_identity) AND TOKEN/HEADER sessions (bearer / api_key / custom_headers, e.g. Devise access-token/client/uid). First call browser_open(url, identity_name) for the integration's site (the page must be logged in AND have called its API), then pass that `page_id` here with `integration_id` or `base_url`. For cookie sessions it captures the full storage_state (incl httpOnly cookies page JS can't read) into the bound identity; for token sessions it captures the auth headers the page sends to the API host and binds them. Re-connects the integration. The captured secret never leaves the server (returns counts only). Generic — any site, any auth scheme, no local Playwright.
    Connector
  • Capture a full-page screenshot of any website as a PNG image. This tool handles all browser automation internally - you don't need to write any code. Simply provide the URL and optionally specify browser actions (click, scroll, wait) to perform before capturing. Returns a presigned download URL for the screenshot (expires in 1 hour). Use this instead of Selenium, Playwright, or puppeteer when you need quick screenshots.
    Connector
  • Scrape a URL then use AI to extract structured JSON data matching your schema description. Combines Playwright scraping with Grok LLM extraction.
    Connector
  • Scrape any URL and return cleaned text content. Powered by Playwright headless browser. Returns title, content, word count.
    Connector