pdfsearch-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_CMD | No | Override the server command used by list-tools/call-tool (e.g. "node dist/src/server.js") | |
| PDF_DIR | No | Directory containing source PDFs (overrides config.json pdfDir) | |
| OCR_LANG | No | OCR language(s) for ocrmypdf (e.g. eng+fra) | eng |
| PDF_PATH | No | Path to the PDF to index | data/AGLC4.pdf |
| INDEX_DIR | No | Directory to store built indexes (overrides config.json indexDir) | |
| OCR_FORCE | No | Force OCR even if a text layer exists (set to 1 to enable) | |
| AUTO_INDEX | No | Scan and build missing/stale indexes on startup (overrides config.json autoIndex) | |
| WATCH_INDEX | No | Watch pdfDir for changes and auto-index (overrides config.json watch) |
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 |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |