loading…
Search for a command to run...
loading…
A local document processing toolkit for AI agents that extracts text, converts PDFs to Markdown, merges files, extracts tables, and summarizes documents without
A local document processing toolkit for AI agents that extracts text, converts PDFs to Markdown, merges files, extracts tables, and summarizes documents without external API dependencies.
By MEOK AI Labs — Sovereign AI tools for everyone.
Document processing toolkit for AI agents. Extract text, convert to Markdown, merge PDFs, extract tables, and summarize documents -- all locally with no external API dependencies.
MCPize MIT License MEOK AI Labs
| Tool | Description |
|---|---|
extract_text_from_pdf |
Extract text content from a PDF file |
convert_pdf_to_markdown |
Convert a PDF document to Markdown format |
merge_pdfs |
Merge multiple PDF files into a single document |
extract_tables |
Extract table-like structures from a PDF page |
summarize_document |
Generate a structural summary of a PDF |
pip install mcp
git clone https://github.com/CSOAI-ORG/pdf-document-mcp.git
cd pdf-document-mcp
python server.py
{
"mcpServers": {
"pdf-document": {
"command": "python",
"args": ["server.py"],
"cwd": "/path/to/pdf-document-mcp"
}
}
}
| Plan | Price | Requests |
|---|---|---|
| Free | $0/mo | 20 calls/day |
| Pro | $9/mo | Unlimited + OCR support + batch processing |
| Enterprise | Contact us | Custom + priority support |
This is one of 255+ MCP servers by MEOK AI Labs. Browse all at meok.ai or GitHub.
MEOK AI Labs | meok.ai | [email protected] | United Kingdom
Добавь это в claude_desktop_config.json и перезапусти Claude Desktop.
{
"mcpServers": {
"pdf-document-mcp-server": {
"command": "npx",
"args": []
}
}
}Web content fetching and conversion for efficient LLM usage.
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also