About io.github.wesseltl/pdf-mcp
io.github.wesseltl/pdf-mcp is an MCP server in the Finance category: extract text and tables from PDFs for an agent: invoices, reports, statements.
Install
uvx pdf-agent-mcppip install pdf-agent-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (11)
docx_table_to_csv(path, index)One Word table as clean CSV text
Parameters not published.
export_document_tables(input_path, output_path, merge_multipage)Export PDF/DOCX tables to `.xlsx`, `.csv`, or `.json`
Parameters not published.
export_with_profile(input_path, profile, output_path)Profile-checked `.xlsx`, `.csv`, or `.json`; XLSX includes Review, Data, and Evidence sheets
Parameters not published.
extract_docx_tables(path)Word tables as rows of cells, with the same assessment fields and merged-cell warnings
Parameters not published.
extract_docx_text(path)Paragraph text from a `.docx` file
Parameters not published.
extract_tables(path, page, merge_multipage)Raw rows, source coordinates, and basic parser warnings
Parameters not published.
extract_text(path, page)Text per page (one page, or the whole doc)
Parameters not published.
extract_with_profile(path, profile)Canonical records, cell evidence, validation issues, and a fail-closed decision
Parameters not published.
list_extraction_profiles()Built-in profile IDs, versions, fields, and hashes
Parameters not published.
page_count(path)How many pages the PDF has
Parameters not published.
table_to_csv(path, page, index)One table as clean CSV text
Parameters not published.
Ask AI
Ask AI about io.github.wesseltl/pdf-mcp
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.