/api/v2/parseParse
Digital PDF → markdown + per-page JSON. Returns docId for downstream calls.
1 credit/page · 0 if cached
MCP for AI agents · REST API
Connect Cursor or Claude to pdf_parse, pdf_extract, pdf_split, and pdf_ask via native MCP — powered by the same REST API for your pipelines.
200 free credits/mo · digital PDFs only · no OCR
{
"mcpServers": {
"rosetta": {
"command": "npx",
"args": ["-y", "docchat-mcp"],
"env": {
"DOCCHAT_API_KEY": "your-api-key",
"DOCCHAT_API_URL": "https://rosettafolio.com"
}
}
}
}Rosetta API key · env vars use DOCCHAT_* (npm package name)
API Hub
Method, path, credits — everything you need before opening the docs.
/api/v2/parseDigital PDF → markdown + per-page JSON. Returns docId for downstream calls.
1 credit/page · 0 if cached
/api/v2/extractStructured field extraction from parsed docs using a JSON schema.
2–4 credits/page
/api/v2/splitAI section detection. Returns page ranges per named section.
2 credits/page
/api/v2/askNatural-language Q&A across one or more parsed documents.
3 credits/page total
Playground
Upload a digital PDF — parse, extract, or split in the browser. No API key required.
Document
Drop PDF here
or open full playground
→ markdown output
→ per-page JSON contents
→ docId for extract / split / ask
response preview
{
"success": true,
"docId": "doc_abc123",
"pageCount": 12,
"markdown": "## Page 1\n..."
}
Quick start
Native MCP
pdf_parse, pdf_extract, pdf_split, pdf_ask — four MCP tools, one npx install. No REST wrapper for your agent.
MCP setup{
"mcpServers": {
"rosetta": {
"command": "npx",
"args": ["-y", "docchat-mcp"],
"env": {
"DOCCHAT_API_KEY": "your-api-key",
"DOCCHAT_API_URL": "https://rosettafolio.com"
}
}
}
}Pricing
One credit ≈ one page processed on most endpoints. Cached parses are free. All four endpoints included on every plan.
Free
$0
200/mo
Starter
$49
3,000/mo
Pro
$99
10,000/mo
Scale
$249
30,000/mo