English Français العربية

Ottersnap MCP

Communauté Médias et design

Glint Render web rendering and evidence API: screenshots, PDFs, OG images, monitoring, extraction and tamper-evident evidence capture.

Code source Documentation

Installation

Les étapes d'installation sont dans la documentation ci-dessous. Documentation

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. ottersnap-mcp
  2. Quick start
  3. Tools
  4. Example prompts
  5. Environment
  6. License

ottersnap-mcp

MCP (Model Context Protocol) server for Glint Render — the web rendering & evidence platform by Moyu. — give Claude, Cursor, Codex and other AI agents eyes on any web page: pixel-perfect screenshots, print-ready PDFs and branded OG images from natural language.

Quick start

Get a free API key at ottersnap.com/dashboard (100 renders/month, no credit card), then add to your MCP client config:

{
  "mcpServers": {
    "glint-render": {
      "command": "npx",
      "args": ["-y", "ottersnap-mcp"],
      "env": {
        "GLINT_API_KEY": "otter_live_your_key_here"
      }
    }
  }
}

Or install globally:

npm install -g ottersnap-mcp
export OTTERSNAP_API_KEY=otter_live_your_key_here
ottersnap-mcp

Tools

ToolWhat it does
render_screenshotRenders any URL and returns the image visually — the agent can actually read the page. Supports full-page, retina 2×, dark mode, element hiding, cookie-banner blocking, iPhone/iPad/Android presets.
render_pdfURL or raw HTML → print-ready PDF (A4/Letter/Legal, landscape, margins, header/footer with page numbers).
create_og_imageBranded 1200×630 social card, returned visually. Seven themes.
extract_pageURL → structured JSON (title, description, headings, links, images, word count) or clean Markdown — built for RAG and agent pipelines.
ai_extractURL + natural-language prompt → structured JSON extracted by LLM.
code_imageCode snippet → macOS-window syntax-highlighted PNG.
check_usageRemaining renders for the configured key.
workflow_createCreate a workflow — an automation that runs steps (screenshot, extract, fetch any public API, AI, email, webhook) on a schedule, when a monitored page changes, or via webhook.
workflow_listList your workflows: trigger, steps, enabled state, last run.
workflow_runRun a workflow immediately and report every step's result.
workflow_runsRecent run history of a workflow.

Example prompts

  • "Screenshot github.com/trending and tell me which repos mention Rust"
  • "Create a workflow that watches my landing page and emails me an AI summary whenever it changes"
  • "Take a dark-mode full-page capture of my landing page and check the footer renders"
  • "Extract every heading and link from https://example.com/docs as markdown"
  • "Scrape the product name, price and rating from this URL into JSON"
  • "Make an OG image for my blog post titled 'Shipping fast with Redis'"
  • "Show this Python function as a pretty code card"
  • "How many OtterSnap renders do I have left?"

Environment

VarRequiredDescription
GLINT_API_KEYyesYour API key (get one free). OTTERSNAP_API_KEY is still accepted for compatibility.
OTTERSNAP_API_URLnoOverride for self-hosting / testing

License

MIT

Questions fréquentes

Qu'est-ce que Ottersnap MCP ?

Glint Render web rendering and evidence API: screenshots, PDFs, OG images, monitoring, extraction and tamper-evident evidence capture.

Comment installer Ottersnap MCP ?

Suivez les étapes d'installation de sa documentation, affichée sur cette page et dans son dépôt.

Ottersnap MCP est-il open source ?

Oui. Son code est sur GitHub sous licence MIT.

Qui maintient Ottersnap MCP ?

Il est publié par zzzjy765. AI.tn le référence sans le maintenir ni le recommander.

Issu des listes communautaires awesome-mcp-servers et du dépôt GitHub du projet. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.