Pdf Tables Mcp
io.github.mehtaphysical13Published by GitHub account mehtaphysical13v0.1.0Updated Oct 24, 2026
Reliable PDF table extraction. Pass a URL, get structured JSON tables with citations.
Overview
Remote MCP server that extracts tables from PDFs given a URL and returns structured JSON with confidence scores and per-cell citations.
- What you can do
- Extract tables from a PDF supplied by URL and return them as structured JSON.
- Get confidence scores and cell-level citations back to the source page.
- Support downstream uses such as RAG preprocessing, data extraction from filings and reports, form-field reading and invoice line-item parsing.
- When to use it
- Useful when an assistant needs tabular data pulled out of PDFs — financial filings, scientific papers, government reports, invoices or compliance forms — and the result should be traceable to the source page. Note the README marks it as an early v0.1 scaffold with tools still coming online.
- Requirements
- A remote endpoint at the provider's hosted URL; no local package or runtime. A bearer token sent in the Authorization header is required, and the README shows a key prefix of pdt_live_. Usage is metered by pages processed per month against a paid tier.
Installation
In SourceWeft
- Open Pdf Tables Mcp in the dashboard and add it to a workspace.
- Connect Authorization token credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.mehtaphysical13%2Fpdf-tables-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"pdf-tables": {
"type": "http",
"url": "https://pdf-tables-mcp.vercel.app/api/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TOKEN>"
}
}
}
}README
pdf-tables-mcp
Reliable PDF table extraction as an MCP tool. Drop into Claude, Cursor, or any MCP-compatible agent and get clean structured JSON tables back from any PDF — with per-cell citations to the source page.
Built by Tool Factory — Tool #2.
🚧 v0.1 scaffold — tools coming online over the next few days.
What it does
Agents drop a PDF URL, get back clean structured JSON tables with confidence scores and cell-level citations back to the source page.
Use cases:
- RAG preprocessing: split tables from text-heavy docs
- Agentic data extraction from financial filings, scientific papers, gov reports
- Form-field reading in compliance workflows
- Receipt/invoice line-item parsing
Pricing
Quotas measure pages processed (not calls) — a 3-page PDF counts as 3 against your monthly quota. Keeps pricing fair for users running small and large PDFs alike.
Install (coming soon)
License
MIT
Source: README.md at commit 1bede11
Tools
0Version history
1- v0.1.0LatestSep 16, 2026
Score
75% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.