ReadAnyDoc
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_API_KEY | No | Set this instead of ANTHROPIC_API_KEY to use OpenAI models as the model provider. | |
| ANTHROPIC_API_KEY | No | Your model provider's key for Claude models (the default provider), e.g. passed with `claude mcp add readanydoc -e ANTHROPIC_API_KEY=your-key -- readanydoc mcp`. | |
| READANYDOC_REFUSAL_READER | No | Optional second model used for pages that the model provider declines (content filtering); without it those pages fall back to plain OCR text at low confidence. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
ReadAnyDoc reads PDFs, scans, photos and Office files. Use parse_document to get a document's text, tables and layout as Markdown. Use extract_fields with a JSON Schema to get typed values; every value comes with citations (the text and page box it was read from). Paths must be files on this computer. Confidence is 'high' or 'low'; check warnings before trusting a result.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| parse_documentA | Parse a local document (PDF, image, DOCX, XLSX, PPTX ...) into Markdown. |
| extract_fieldsB | Extract structured values from a local document into a JSON Schema, with citations. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
parse_document converts a document to Markdown, while extract_fields pulls structured values into a JSON Schema, so their outputs and use cases are clearly different. There is mild overlap since extraction implicitly parses the same file, but the descriptions make the boundary (freeform text vs. schema-bound values) reasonably clear.
Both tools follow the same snake_case verb_noun convention (parse_document, extract_fields) with no deviations. The naming is predictable and immediately readable.
Two tools is on the thin side, but for a focused document-reading server they cover the two core workflows: raw conversion and structured extraction. Both tools earn their place, though a third (e.g. batch or format listing) could add value.
The surface covers the main lifecycle: read a document and extract structured data with citations, across many formats and page ranges. Minor gaps exist, such as no batch/multi-file processing, no remote URL input, and no chunking guidance for very large documents.