Paper Reader MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PAPER_READER_CACHE | No | Cache directory. Defaults to %LOCALAPPDATA%\.paper-reader-mcp. | %LOCALAPPDATA%\paper-reader-mcp |
| PAPER_READER_MODELS | No | Offline Docling model directory. | |
| PAPER_READER_OCR_MODE | No | OCR mode: 'auto', 'on', or 'off'. | auto |
| PAPER_READER_TABLE_MODE | No | Table model quality: 'fast' or 'accurate'. | fast |
| PAPER_READER_PDF_PIPELINE | No | PDF pipeline mode: 'standard' or reduced quality fallback 'native'. | standard |
| PAPER_READER_FORMULA_MODEL | No | Formula model: 'off', 'codeformulav2', or 'granite_docling'. | off |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| paper_ingestB | Parse one research file into cached evidence and referenced images. |
| paper_searchC | Return compact, ranked Markdown evidence with page hints and linked image paths. |
| paper_batch_searchC | Retrieve adaptively bounded evidence for up to 32 questions in one MCP call. |
| paper_visualB | Return exactly one relevant extracted image or one on-demand original PDF page/crop. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |