ToolsMCP
PDF Text, Table and OCR Extractor
Listed in the official MCP Registry with a hosted streamable-http endpoint. Capabilities below are the publisher’s own description.
- Type
- MCP server
- Publisher
- bkeller-research (GitHub)
- Prerequisites
- An MCP client that supports streamable-http. No credential header is declared in the registry record.
- Current version
- 0.1.0 · updated
- Official links
Publisher’s description
PDF URLs to per-page text, tables as rows, Markdown, metadata and OCR for scanned pages.
Evidence
Each record keeps its own date and scope. Labels are independent: documentation does not imply a checked connection, and a connection does not imply a passed task.
-
Listed in the official MCP Registry
Version 0.1.0, registry status active. 1 remote endpoint (streamable-http)
Publisher-supplied registry metadata. Not a checked connection, a safe package or a completed task.
- Source publisher
- bkeller-research (GitHub)
- Version observed
- 0.1.0
- Source
- registry.modelcontextprotocol.io/v0.1/servers/io.github.bkeller-research%2Fpdf-text-table-ocr-extractor/versions/0.1.0
Listed for these tasks
| Task | Documented for this task | Unknowns | Why it is listed |
|---|---|---|---|
| Extract structured data from PDFs | Publisher description mentions “pdf”, “ocr”. | No connection check or task run. Capability is as described by the publisher. | Rule pdf-extraction matched: “pdf”, “ocr”. Rule pdf-extraction. |
Published pricing
No published price recordedCost per completed task is only shown on a task page when a comparable run recorded metered spend and verified completions.
Registry record
- Remote endpoints
https://mcp.apify.com/?tools=brenton8907/pdf-text-table-ocr-extractor(streamable-http)- Registry entry
- Official MCP Registry record (JSON)
- Namespace
io.github.bkeller-research/pdf-text-table-ocr-extractor
AgentsByTask never installs discovered packages or connects to discovered endpoints during discovery. An endpoint string in a registry record is not a checked connection.