@synoppy/mcp
OfficialClick on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@synoppy/mcpRead the markdown from https://example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@synoppy/mcp
Give your AI agent the whole web. An MCP server for Synoppy — drop it into Claude Desktop, Cursor, or any MCP client and your agent gets tools to read, crawl, map, extract, classify, enrich, screenshot, and pull images from the live web.
Get a free key → · Docs · synoppy.com
Every tool returns the full JSON response, including the metered billing fields creditsUsed and creditsRemaining.
Tools
Tool | Endpoint | Inputs |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| one of |
|
|
|
synoppy_read— URL → clean markdown / HTML / text plus page metadata (title, description, language, statusCode, wordCount, rendered, bytesIn…). Passrender: "auto"to render JS-heavy pages on demand.synoppy_screenshot— full-page or viewport PNG as a data URL. Requires rendering credits; may returnRENDER_UNAVAILABLE.synoppy_crawl— crawl a site, read each page (pages[],discovered,count).synoppy_map— every URL on a domain (source: "sitemap" | "links").synoppy_extract— AI structured-JSON extraction. Returnsdata,usagetokens,truncated, andmodel.synoppy_classify— industry (NAICS/SIC) by default, or customlabelsmode ({ label, matched, confidence, reasoning }).synoppy_enrich— brand profile (name, logo, colors, fonts, socials, address) from a URL, bare domain, or work email.synoppy_images— every image withsrc,alt,width,height.
Not live yet (coming soon):
/api/act. This is intentionally not exposed as a tool.
Related MCP server: crawl4ai-mcp
Setup
Claude Desktop — claude_desktop_config.json
{
"mcpServers": {
"synoppy": {
"command": "npx",
"args": ["-y", "@synoppy/mcp"],
"env": { "SYNOPPY_API_KEY": "syn_xxxxxxxxxxxx" }
}
}
}Cursor — ~/.cursor/mcp.json (same shape)
Create a key in the dashboard. The server reads
SYNOPPY_API_KEY (auth header Authorization: Bearer syn_...) from its
environment; set SYNOPPY_BASE_URL to point at a self-hosted instance.
Credits
Synoppy is metered. Every successful response carries creditsUsed (number) and
creditsRemaining (number or null), and the tools surface them verbatim. For
example, synoppy_read returns:
{
"success": true,
"metadata": { "title": "Example", "statusCode": 200, "wordCount": 412, "rendered": false, "bytesIn": 18233 },
"markdown": "# Example...",
"latencyMs": 284,
"creditsUsed": 1,
"creditsRemaining": 4999
}Watch creditsRemaining to track your balance as you go.
Local dev
npm install
npm run build
SYNOPPY_API_KEY=syn_... npm startThe published package ships a single bundled, minified dist/index.js (with the
#!/usr/bin/env node shebang preserved) plus generated dist/index.d.ts types —
no readable source.
MIT licensed.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Synoppy/synoppy-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server