Prompt-ready content.
Readable extracted content for summaries, reasoning, and answer generation.
First successful request
Use this path when you want to connect Sinyx to an AI agent, RAG pipeline, research assistant, or MCP client without building your own extraction and cleanup layer.
Subscribe to Sinyx on RapidAPI, then use the generated app key with the RapidAPI host header.
x-rapidapi-host: sinyx.p.rapidapi.com
x-rapidapi-key: YOUR_RAPIDAPI_KEY
Start with a stable public URL. The important part is format: "context".
curl --request POST \
--url https://sinyx.p.rapidapi.com/v1/extract \
--header 'Content-Type: application/json' \
--header 'x-rapidapi-host: sinyx.p.rapidapi.com' \
--header 'x-rapidapi-key: YOUR_RAPIDAPI_KEY' \
--data '{
"url": "https://example.com",
"format": "context"
}'
A successful agent-context response should include Markdown, chunks, citation, freshness, and quality signals.
Readable extracted content for summaries, reasoning, and answer generation.
Semantic sections with heading paths, priority scores, and chunk text.
Domain, canonical URL, fetched time, freshness signal, and quality score.
For Node workflows, shape the response into the context your agent should see.
const page = await response.json();
const agentContext = {
source: page.citation,
freshness: page.freshness,
quality: page.quality,
topChunks: page.chunks.slice(0, 3),
markdown: page.markdown
};
The published sinyx-mcp package defaults extraction tools to context, which keeps MCP clients aligned with agent workflows.
{
"mcpServers": {
"sinyx": {
"command": "npx",
"args": ["-y", "sinyx-mcp"],
"env": {
"SINYX_API_BASE_URL": "https://sinyx.p.rapidapi.com",
"SINYX_API_KEY": "YOUR_RAPIDAPI_KEY",
"SINYX_API_KEY_HEADER": "x-rapidapi-key",
"SINYX_RAPIDAPI_HOST": "sinyx.p.rapidapi.com"
}
}
}
}
The strongest first use cases are agents that need fresh public documentation, source-aware research notes, product-page ingestion, or safer URL handling for user-provided links.