Hosted document tools for agents: extract, parse, classify, convert, OCR, sign, and redact.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
Scored across 14 tools
Most tools map to distinct operations (upload, parse, extract, classify, redact, sign, process), but several clusters overlap: get_run vs read_result vs get_processor_job all read run/job state, parse_document vs process_document both touch conversion, and redact_document overlaps with process_document's createRedactions actions. Descriptions actively disambiguate these (e.g. 'Do not use get_run/read_result for Processor jobs', 'For PDF-to-Markdown prefer parse_document'), which rescues the set from confusion.
Nearly all names follow a verb_noun snake_case pattern: classify_document, extract_fields, generate_schema, get_run, read_result, upload_documents, etc. The one clear outlier is studio_run_link (a noun phrase with no verb), and open_in_dws_viewer is a slightly looser verb phrase, but the convention is otherwise predictable.
14 tools is well within the healthy range and each tool earns its place: upload, three analysis paths (parse/extract/classify), schema preview, Build processing, redaction, signing, run/job status, result reading, usage, and viewer entry points. No tool appears redundant enough to drop.
The surface covers the document lifecycle well: upload, process, analyze, preview schemas, sign, redact, poll status, read results, save outputs, and check usage. Gaps remain around cancellation (explicitly noted as absent), run listing/history, and document deletion (viewer documents persist until deleted but no delete tool exists), though agents can mostly work around these.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
classify_documentextract_fieldsgenerate_schemaget_account_usageget_processor_jobget_runopen_in_dws_viewerparse_documentprocess_documentread_resultredact_documentsign_documentstudio_run_linkupload_documentsDocument conversion and OCR for AI agents: PDF, Office docs, images to text.
Document creation, signing requests, and approval workflows for AI agents over Streamable HTTP.
Pay-per-call document and web tools for AI agents: PDF parsing and OCR (Japanese-strong), web and structured extraction, invoice verification, company profiles and PDF utilities. x402 (USDC on Base), no API key; failed calls are never charged.
Turn documents into structured data: parse, extract, classify, split, and fill PDF forms.
Add one secure layer between your agents and this server.
