ParseHub.dev is a hosted document-to-records service with a remote MCP server. Agents can upload a CSV, PDF, or Word file, summarize and analyze CSV data (filter, sort, group_by, and more), read text from PDF and Word files, extract attendees, agenda items, and action items from meeting notes, ask a question about an uploaded document, and store files as database records to list and read later.
Each account sees only its own files and records.
Endpoint: https://parsehub.dev/mcp (Streamable HTTP, stateless)
Auth: API key in the X-API-Key header (keys start with mcp_), or Authorization: Bearer <API key or JWT>. Every request without credentials returns 401.
Plans: Free (100 API requests/month, 1 document upload), or 5,000 requests/month on the $9/month or $42/year plan. Every MCP request counts toward the allowance.
Tools: upload_csv, summarize_csv, analyze_csv, upload_document, read_document, extract_meeting_notes, ask_document, database_status, list_database_documents, get_database_document, store_document, extract_stored_meeting_notes, export_database (administrators only).
Not affiliated with ParseHub (parsehub.com), the web-scraping tool. ParseHub.dev does not scrape websites.
By Poietes LLC. Docs: https://parsehub.dev/guide#connect-via-mcp
Scored across 13 tools
Most tools target clearly distinct resources and actions (upload vs store vs read vs ask vs get/list). The closest confusable pairs are extract_meeting_notes vs extract_stored_meeting_notes and analyze_csv vs summarize_csv, but descriptions differentiate them adequately (upload-dir vs stored-and-saved; transform vs summarize).
Nearly all tools follow a consistent verb_noun pattern (read_document, store_document, upload_csv, list_database_documents, etc.). The one clear deviation is database_status, which lacks a verb, and export_database uses a noun-as-destination but remains readable.
13 tools sit comfortably in the well-scoped 3-15 range for a document-ingestion-and-analysis server. Each tool maps to a distinct step (upload, store, read, extract, query, CSV ops, DB admin) without obvious redundancy.
Core lifecycle is covered (upload, store, list, get, read, ask, extract, CSV analyze/summarize), but there is no delete or update operation for stored documents, and no tool to list files in the caller's upload directory, forcing agents to know filenames ahead of time. Export and status exist but CRUD is only partially complete.
Analyze a CSV file. operations is a JSON list of filter, sort, drop_columns, rename_columns, fill_na, drop_na, or group_by steps.
Inputs: file_path (required), operations (required).
Answer a question about a document in the caller's own upload directory.
Inputs: question (required), file_path (required).
Report database connections and how many documents are stored for the caller.
Inputs: no named parameters.
Copy data from one configured database to another. Administrators only.
Inputs: source_db (required), target_db (required).
Extract attendees, agenda items, and action items from a document the caller owns.
Inputs: file_path (required).
Extract meeting notes from a stored document and save them for the caller.
Inputs: document_id (required).
Read one stored document, including its content when include_content is true.
Inputs: document_id (required), include_content.
List documents stored in the database for the caller.
Inputs: limit, file_type.
Read text from a PDF or Word file in the caller's own upload directory.
Inputs: file_path (required).
Process an uploaded file into the database. The file must already belong to the caller.
Inputs: file_path (required), file_type (required), filename, store_in_db, +1 more.
Summarize a CSV file in the caller's own upload directory.
Inputs: file_path (required).
Upload a CSV file for the signed-in user. content is the CSV text.
Inputs: content (required), filename (required).
Upload a PDF or Word file. content_base64 is the file bytes, and doc_type may be meeting_notes.
Inputs: filename (required), content_base64 (required), doc_type.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Hosted MCP: CSV/XLSX to JSON rows and text-PDF pages; private uploads or URLs, no API key.
Hosted MCP server: convert PDFs to clean, LLM-ready Markdown with tables, formulas and OCR.
Teable is an AI spreadsheet for business that combines a familiar spreadsheet interface with a structured database. Its remote MCP server lets AI agents inspect project and table structure, read and update records, and access the Teable API through OAuth with existing project permissions. Website: [teable.ai](https://teable.ai)
Hosted document tools for agents: extract, parse, classify, convert, OCR, sign, and redact.
Add one secure layer between your agents and this server.
