MCP PDF Reader
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BAIDU_OCR_API_KEY | No | Your Baidu OCR API Key for OCR functionality | |
| BAIDU_OCR_SECRET_KEY | No | Your Baidu OCR Secret Key for OCR functionality |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| read-pdf-smartD | – |
| read-pdfD | – |
| search-pdfD | – |
| pdf-metadataD | – |
| ocr-pdf-legacyD | – |
| ocr-pdf-auto-legacyD | – |
| smart-read-pdf-legacyD | – |
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 7 tools
Multiple tools have unclear boundaries and overlapping purposes, particularly between read-pdf, read-pdf-smart, smart-read-pdf-legacy, ocr-pdf-auto-legacy, and ocr-pdf-legacy. The lack of descriptions exacerbates the ambiguity, making it difficult to distinguish their specific functions.
The naming follows a mixed convention with hyphenated names (e.g., read-pdf) and inconsistent suffixes like 'legacy' and 'smart'. While readable, there is no clear pattern, such as a consistent verb_noun structure, leading to some confusion.
With 7 tools, the count is reasonable for a PDF reader server, suggesting a well-scoped set. However, the lack of descriptions makes it hard to assess if each tool earns its place, but the number itself is appropriate.
Inferred domain includes reading, OCR, metadata, and search, but there are significant gaps such as no tools for editing, converting, or managing PDFs (e.g., merge, split, annotate). The surface is incomplete for typical PDF operations, likely causing agent failures.