summarize_document — PreteWorks API MCP Tool
summarize_document
(summarize document) is one of 29 tools on the
PreteWorks API
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call summarize_document from your client
- Claude Code PreteWorks API summarize_document run in your project directory
- Claude Desktop PreteWorks API summarize_document ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor PreteWorks API summarize_document ~/.cursor/mcp.json
- VS Code PreteWorks API summarize_document .vscode/mcp.json
- Zed PreteWorks API summarize_document ~/.config/zed/settings.json
- Windsurf PreteWorks API summarize_document ~/.codeium/windsurf/mcp_config.json
- Cline PreteWorks API summarize_document ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI PreteWorks API summarize_document ~/.gemini/settings.json
- Grok PreteWorks API summarize_document .mcp.json (in your project root)
- ChatGPT PreteWorks API summarize_document Settings → Connectors → Advanced → Developer mode
- Claude.ai PreteWorks API summarize_document Settings → Connectors → Add custom connector
- LangChain PreteWorks API summarize_document pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http preteworks-api https://api.preteworks.com/mcp
Other tools on this server
- render_html_to_pdf
- number_pdf
- pdf_info
- set_pdf_metadata
- render_document
- merge_pdfs
- select_pages
- rotate_pdf
- watermark_pdf
- extract_pdf_text
- images_to_pdf
- markdown_to_pdf
- split_pdf
- read_pdf_form
- fill_pdf_form
- file_to_markdown
- data_to_spreadsheet
- batch_scrape
- crawl_site
- map_site
- extract_data
- answer_from_document
- docx_to_text
- docx_to_pdf
- read_url
- url_to_pdf
- url_to_screenshot
- scrape_page
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.