noteker
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ANTHROPIC_API_KEY | Yes | Anthropic API key (sk-ant-...). Can also be set in settings.yaml. | |
| NOTEKER_CONFIG_DIR | No | Override config directory path. |
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": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| noteker_process_pdfA | Convert a local PDF of handwritten notes into clean Markdown using Claude Vision. file_path: absolute path to a PDF file on the local filesystem. note_context: optional hint about the content (e.g. 'team meeting 2025-06-20'). Helps Claude resolve ambiguous words. page_start: first page to process (1-based, inclusive). Omit to start from page 1. page_end: last page to process (1-based, inclusive). Omit to process to the last page (capped at max_pages when no range is given). Pages are sent to Claude Vision in batches of at most 5. Requests spanning more pages are processed as several sequential batches and stitched into one result — the caller always gets back a single combined Markdown document. |
| noteker_statusA | Return Noteker version and configuration status. |
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
Only two tools with clearly distinct purposes: one processes PDFs into Markdown, the other returns server status. No overlap whatsoever.
Both tools use the same prefix 'noteker_' and follow a verb_noun pattern ('process_pdf', 'status'), making naming predictable and consistent.
With only two tools, the server is minimal but well-scoped for its stated purpose of converting handwritten notes from PDFs. Slightly low but reasonable.
The core functionality (PDF conversion) is fully covered, and a status tool is provided. Minor gaps like batch processing or format options are absent but not essential.