Extract tables, text and formulas from PDFs, including scanned pages and broken text layers.
Connect Remote server
claude mcp add --transport http pdfintact https://mcp.pdfintact.com/mcp
{
"mcpServers": {
"pdfintact": {
"url": "https://mcp.pdfintact.com/mcp"
}
}
}
{
"servers": {
"pdfintact": {
"type": "http",
"url": "https://mcp.pdfintact.com/mcp"
}
}
}
Settings > Connectors > Add custom connector
URL: https://mcp.pdfintact.com/mcp
Tools 3 found in our last check
convert_pdfConvert a PDF into structured content (tables, charts, formulas, headings, body text) using a two-stage pipeline (layout detection, then a vision-language model) rather than a single VLM call on the raw PDF -- calling a VLM on a raw PDF directly is a known-unreliable pattern for…
get_resultFetch the status and (once finished) the structured result of a job previously created by convert_pdf. Poll this with the job_handle convert_pdf returned until _meta.state is "done" or "failed" -- do not call convert_pdf again while waiting. job_handle is scoped to the account t…
get_balanceCheck the current PDFIntact credit balance for the authenticated account (1 page = 1 credit), plus the soonest-expiring credit lot. Useful before submitting a large PDF to convert_pdf, or after an insufficient_credits error to see how many credits are needed and get a purchase l…
Details
| Endpoint | https://mcp.pdfintact.com/mcp (Streamable HTTP) |
| First published | 2 Sep 2026 |
| Last updated | 2 Sep 2026 |
| Registry name | com.pdfintact/pdfintact |
More security servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.
