OtterSnap
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OTTERSNAP_API_KEY | Yes | Your API key from ottersnap.com/#getkey | |
| OTTERSNAP_API_URL | No | Override for self-hosting / testing |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| render_screenshotA | Render a web page to an image and return it visually — gives the calling agent eyes on any URL. Supports full-page captures, retina scale, dark mode, element selection and cookie-banner blocking. |
| render_pdfB | Render a web page (or raw HTML) to a print-ready PDF file. Returns size info; PDF bytes are not inlined. |
| create_og_imageA | Generate a branded 1200x630 Open Graph social card and return it visually. |
| check_usageA | Check remaining renders and quota for the configured OtterSnap key. |
| extract_pageA | Extract structured content from a web page: title, description, headings, links, images and the page body as clean Markdown — ready to feed to an LLM. This READS the page (use render_screenshot to SEE it). |
| ai_extractA | Extract structured data from a web page using natural language. Give a URL, describe what you want (e.g. 'all product names and prices'), receive JSON. Powered by an LLM reading the rendered page. |
| code_imageA | Turn a code snippet into a beautiful syntax-highlighted PNG (macOS-style window card). Great for sharing code on social media or docs. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool has a distinct output type or purpose: PDF, OG image, usage check, markdown extraction, AI JSON extraction, code image, and screenshot. However, extract_page and ai_extract overlap in that both pull content from a page, and create_og_image could be conflated with render_screenshot since both produce visual outputs.
Most tools follow a verb_noun pattern (render_pdf, create_og_image, check_usage, extract_page, render_screenshot), but ai_extract inverts the pattern (noun_verb) and code_image is a noun_noun compound. The mix of render_* and extract_* prefixes is readable but inconsistent.
Seven tools is a well-scoped set for a rendering and extraction utility API. Each tool covers a distinct common use case without redundancy or bloat, fitting comfortably in the ideal 3-15 range.
The set covers the core workflows: rendering to PDF and screenshot, generating social images, extracting page content in two modes, and monitoring usage. Minor gaps exist, such as no batch processing, no way to retrieve previously generated outputs by ID, and no direct URL-based PDF delivery (since bytes are not inlined), but the surface is largely complete for its stated domain.