techtenstein-pdf-mcp 1.0.0__tar.gz

techtenstein_pdf_mcp-1.0.0/PKG-INFO

@@ -0,0 +1,128 @@
+Metadata-Version: 2.4
+Name: techtenstein-pdf-mcp
+Version: 1.0.0
+Summary: MCP server for Techtenstein PDF Extract API. Fast PDF text + tables via Claude, Cline, and Cursor.
+Project-URL: Homepage, https://apis.techtenstein.com
+Project-URL: Documentation, https://pdf.api.techtenstein.com
+Project-URL: Repository, https://github.com/sathvic-kollu/techtenstein-pdf-mcp
+Author-email: Sathvic Kollu <sathvic777@gmail.com>
+License: MIT
+Keywords: api,claude,extract,mcp,ocr,pdf,tables,techtenstein
+Classifier: Development Status :: 4 - Beta
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.10
+Requires-Dist: fastmcp>=0.2.0
+Requires-Dist: requests>=2.31.0
+Description-Content-Type: text/markdown
+
+# Techtenstein PDF MCP
+
+MCP server that gives your Claude, Cline, or Cursor session the ability to extract
+text, tables, and metadata from any PDF URL — including scanned PDFs via OCR.
+Powered by the [Techtenstein PDF Extract API](https://apis.techtenstein.com).
+
+## Tools exposed
+
+- `pdf_extract_text(pdf_url, ocr=False)` — Extract all text from a PDF as clean plain text
+- `pdf_extract_tables(pdf_url)` — Extract all tables as structured row arrays
+- `pdf_metadata(pdf_url)` — Get title, author, page count, creation date, encryption status
+
+## Install (Claude Desktop)
+
+Add to `~/Library/Application Support/Claude/claude_desktop_config.json`:
+
+```json
+{
+  "mcpServers": {
+    "techtenstein-pdf": {
+      "command": "uvx",
+      "args": ["techtenstein-pdf-mcp"],
+      "env": {
+        "TECHTENSTEIN_API_KEY": "your_key_from_techtenstein.com"
+      }
+    }
+  }
+}
+```
+
+Restart Claude Desktop. `pdf_extract_text`, `pdf_extract_tables`, and `pdf_metadata` will appear as available tools.
+
+## Install (Cline / VS Code)
+
+Cline auto-detects MCP servers from your Claude Desktop config. Same setup as above works.
+
+## Install (Cursor)
+
+Add to `~/.cursor/mcp.json`:
+
+```json
+{
+  "mcpServers": {
+    "techtenstein-pdf": {
+      "command": "uvx",
+      "args": ["techtenstein-pdf-mcp"],
+      "env": {"TECHTENSTEIN_API_KEY": "your_key"}
+    }
+  }
+}
+```
+
+## Get an API key
+
+Free tier (50 extractions/day, no card): https://apis.techtenstein.com
+
+Paid tiers start at $5/month for 2,000 extractions.
+
+## Example usage
+
+Once installed, ask Claude:
+
+> "Extract the tables from this earnings report PDF: https://example.com/q4.pdf"
+
+Claude will call `pdf_extract_tables` and return a clean structured view of every table on the page.
+
+Or for scanned documents:
+
+> "This PDF is a scanned invoice. Extract the text: https://example.com/invoice.pdf"
+
+Claude will call `pdf_extract_text(pdf_url, ocr=True)` and read the image-based text via OCR.
+
+## Response schema (text mode)
+
+```json
+{
+  "text": "Full extracted body text...",
+  "page_count": 12,
+  "word_count": 3450,
+  "ms": 240
+}
+```
+
+## Response schema (tables mode)
+
+```json
+{
+  "tables": [
+    {
+      "page": 3,
+      "rows": [
+        ["Product", "Q1", "Q2", "Q3", "Q4"],
+        ["Widget A", "1200", "1350", "1420", "1600"]
+      ]
+    }
+  ]
+}
+```
+
+## Support
+
+- Docs: https://apis.techtenstein.com
+- Issues: https://github.com/sathvic-kollu/techtenstein-pdf-mcp/issues
+- Email: sathvic777@gmail.com
+
+## License
+
+MIT

techtenstein_pdf_mcp-1.0.0/README.md

@@ -0,0 +1,108 @@
+# Techtenstein PDF MCP
+
+MCP server that gives your Claude, Cline, or Cursor session the ability to extract
+text, tables, and metadata from any PDF URL — including scanned PDFs via OCR.
+Powered by the [Techtenstein PDF Extract API](https://apis.techtenstein.com).
+
+## Tools exposed
+
+- `pdf_extract_text(pdf_url, ocr=False)` — Extract all text from a PDF as clean plain text
+- `pdf_extract_tables(pdf_url)` — Extract all tables as structured row arrays
+- `pdf_metadata(pdf_url)` — Get title, author, page count, creation date, encryption status
+
+## Install (Claude Desktop)
+
+Add to `~/Library/Application Support/Claude/claude_desktop_config.json`:
+
+```json
+{
+  "mcpServers": {
+    "techtenstein-pdf": {
+      "command": "uvx",
+      "args": ["techtenstein-pdf-mcp"],
+      "env": {
+        "TECHTENSTEIN_API_KEY": "your_key_from_techtenstein.com"
+      }
+    }
+  }
+}
+```
+
+Restart Claude Desktop. `pdf_extract_text`, `pdf_extract_tables`, and `pdf_metadata` will appear as available tools.
+
+## Install (Cline / VS Code)
+
+Cline auto-detects MCP servers from your Claude Desktop config. Same setup as above works.
+
+## Install (Cursor)
+
+Add to `~/.cursor/mcp.json`:
+
+```json
+{
+  "mcpServers": {
+    "techtenstein-pdf": {
+      "command": "uvx",
+      "args": ["techtenstein-pdf-mcp"],
+      "env": {"TECHTENSTEIN_API_KEY": "your_key"}
+    }
+  }
+}
+```
+
+## Get an API key
+
+Free tier (50 extractions/day, no card): https://apis.techtenstein.com
+
+Paid tiers start at $5/month for 2,000 extractions.
+
+## Example usage
+
+Once installed, ask Claude:
+
+> "Extract the tables from this earnings report PDF: https://example.com/q4.pdf"
+
+Claude will call `pdf_extract_tables` and return a clean structured view of every table on the page.
+
+Or for scanned documents:
+
+> "This PDF is a scanned invoice. Extract the text: https://example.com/invoice.pdf"
+
+Claude will call `pdf_extract_text(pdf_url, ocr=True)` and read the image-based text via OCR.
+
+## Response schema (text mode)
+
+```json
+{
+  "text": "Full extracted body text...",
+  "page_count": 12,
+  "word_count": 3450,
+  "ms": 240
+}
+```
+
+## Response schema (tables mode)
+
+```json
+{
+  "tables": [
+    {
+      "page": 3,
+      "rows": [
+        ["Product", "Q1", "Q2", "Q3", "Q4"],
+        ["Widget A", "1200", "1350", "1420", "1600"]
+      ]
+    }
+  ]
+}
+```
+
+## Support
+
+- Docs: https://apis.techtenstein.com
+- Issues: https://github.com/sathvic-kollu/techtenstein-pdf-mcp/issues
+- Email: sathvic777@gmail.com
+
+## License
+
+MIT

techtenstein_pdf_mcp-1.0.0/mcp-server.json

@@ -0,0 +1,44 @@
+{
+  "$schema": "https://github.com/modelcontextprotocol/registry/schemas/mcp-server.schema.json",
+  "name": "techtenstein-pdf",
+  "description": "Fast PDF text & table extraction. Powered by Techtenstein PDF API.",
+  "version": "1.0.0",
+  "author": {
+    "name": "Sathvic Kollu",
+    "email": "sathvic777@gmail.com",
+    "url": "https://techtenstein.com"
+  },
+  "homepage": "https://apis.techtenstein.com",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/sathvic-kollu/techtenstein-pdf-mcp"
+  },
+  "license": "MIT",
+  "keywords": ["pdf", "extract", "ocr", "tables", "documents"],
+  "runtime": "python",
+  "install": {
+    "uvx": "uvx techtenstein-pdf-mcp",
+    "pip": "pip install techtenstein-pdf-mcp"
+  },
+  "env": [
+    {
+      "name": "TECHTENSTEIN_API_KEY",
+      "description": "API key from https://apis.techtenstein.com (free tier available)",
+      "required": false
+    }
+  ],
+  "tools": [
+    {
+      "name": "pdf_extract_text",
+      "description": "Extract all text from a PDF URL as clean plain text. Supports OCR for scanned PDFs."
+    },
+    {
+      "name": "pdf_extract_tables",
+      "description": "Extract all tables from a PDF as structured row arrays."
+    },
+    {
+      "name": "pdf_metadata",
+      "description": "Get PDF metadata: title, author, page count, creation date, encryption status."
+    }
+  ]
+}

techtenstein_pdf_mcp-1.0.0/pyproject.toml

@@ -0,0 +1,34 @@
+[project]
+name = "techtenstein-pdf-mcp"
+version = "1.0.0"
+description = "MCP server for Techtenstein PDF Extract API. Fast PDF text + tables via Claude, Cline, and Cursor."
+readme = "README.md"
+authors = [
+    { name = "Sathvic Kollu", email = "sathvic777@gmail.com" }
+]
+license = { text = "MIT" }
+keywords = ["mcp", "pdf", "extract", "ocr", "tables", "claude", "techtenstein", "api"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+]
+requires-python = ">=3.10"
+dependencies = [
+    "fastmcp>=0.2.0",
+    "requests>=2.31.0",
+]
+
+[project.urls]
+Homepage = "https://apis.techtenstein.com"
+Documentation = "https://pdf.api.techtenstein.com"
+Repository = "https://github.com/sathvic-kollu/techtenstein-pdf-mcp"
+
+[project.scripts]
+techtenstein-pdf-mcp = "server:mcp.run"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"

techtenstein_pdf_mcp-1.0.0/server.py

@@ -0,0 +1,120 @@
+"""Techtenstein PDF Extract MCP Server.
+
+Wraps the Techtenstein PDF Extract REST API and exposes it as MCP tools.
+Claude Desktop, Cline, Cursor, and any MCP-compatible client can invoke
+`pdf_extract_text`, `pdf_extract_tables`, or `pdf_metadata` on any PDF URL.
+
+Install:
+    pip install fastmcp requests
+    export TECHTENSTEIN_API_KEY=your_key
+
+Run:
+    python server.py
+
+Or via uvx:
+    uvx techtenstein-pdf-mcp
+"""
+
+import base64
+import os
+import sys
+import requests
+from fastmcp import FastMCP
+
+API_BASE = os.getenv("TECHTENSTEIN_PDF_API_BASE", "https://pdf.api.techtenstein.com")
+API_KEY = os.getenv("TECHTENSTEIN_API_KEY", "")
+
+mcp = FastMCP(
+    name="techtenstein-pdf",
+    version="1.0.0",
+    description="Fast PDF text & table extraction. Powered by Techtenstein PDF API.",
+)
+
+
+def _headers() -> dict:
+    return {"X-API-Key": API_KEY} if API_KEY else {}
+
+
+@mcp.tool()
+def pdf_extract_text(pdf_url: str, ocr: bool = False) -> dict:
+    """
+    Extract all text from a PDF URL as clean plain text.
+
+    Args:
+      pdf_url: HTTPS URL of the PDF to extract.
+      ocr: Set true for scanned PDFs (uses Tesseract, slower but works on images).
+
+    Returns:
+      { "text": "...", "page_count": 12, "word_count": 3450, "ms": 240 }
+    """
+    if not pdf_url.startswith(("http://", "https://")):
+        return {"error": "pdf_url must include http:// or https://"}
+    try:
+        r = requests.post(
+            f"{API_BASE}/extract",
+            json={"url": pdf_url, "mode": "text", "ocr": ocr},
+            headers=_headers(),
+            timeout=90,
+        )
+        r.raise_for_status()
+        return r.json()
+    except requests.RequestException as e:
+        return {"error": str(e)}
+
+
+@mcp.tool()
+def pdf_extract_tables(pdf_url: str) -> dict:
+    """
+    Extract all tables from a PDF as structured JSON (list of row arrays per table).
+
+    Args:
+      pdf_url: HTTPS URL of the PDF.
+
+    Returns:
+      { "tables": [ { "page": 3, "rows": [ [ "col1", "col2" ], ... ] } ] }
+    """
+    if not pdf_url.startswith(("http://", "https://")):
+        return {"error": "pdf_url must include http:// or https://"}
+    try:
+        r = requests.post(
+            f"{API_BASE}/extract",
+            json={"url": pdf_url, "mode": "tables"},
+            headers=_headers(),
+            timeout=90,
+        )
+        r.raise_for_status()
+        return r.json()
+    except requests.RequestException as e:
+        return {"error": str(e)}
+
+
+@mcp.tool()
+def pdf_metadata(pdf_url: str) -> dict:
+    """
+    Extract PDF metadata (title, author, page count, creation date, encryption status).
+
+    Args:
+      pdf_url: HTTPS URL of the PDF.
+
+    Returns:
+      { "title": "...", "author": "...", "pages": 42, "created": "2026-01-15", "encrypted": false }
+    """
+    if not pdf_url.startswith(("http://", "https://")):
+        return {"error": "pdf_url must include http:// or https://"}
+    try:
+        r = requests.post(
+            f"{API_BASE}/extract",
+            json={"url": pdf_url, "mode": "metadata"},
+            headers=_headers(),
+            timeout=30,
+        )
+        r.raise_for_status()
+        return r.json()
+    except requests.RequestException as e:
+        return {"error": str(e)}
+
+
+if __name__ == "__main__":
+    if not API_KEY:
+        print("WARNING: TECHTENSTEIN_API_KEY not set. Free tier only (50 extractions/day).", file=sys.stderr)
+    mcp.run()