Document Extractor MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEBUG | No | Enable debug logging | false |
| NODE_ENV | No | Environment mode (development or production) | development |
| HTTP_PORT | No | Port number for HTTP mode | 3000 |
| POCKETBASE_URL | No | PocketBase server URL | http://127.0.0.1:8090 |
| READ_ONLY_MODE | No | Disable write operations | false |
| TRANSPORT_MODE | No | Transport mode for the server (stdio or http) | stdio |
| DOCUMENTS_COLLECTION | No | Collection name for documents | documents |
| AUTO_CREATE_COLLECTION | No | Auto-create collections on startup | true |
| POCKETBASE_ADMIN_EMAIL | Yes | Admin email for PocketBase authentication | |
| POCKETBASE_ADMIN_PASSWORD | Yes | Admin password for PocketBase authentication |
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
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| extract_documentA | Extract document content from Microsoft Learn or GitHub URL and store in PocketBase |
| authenticateC | Test authentication with PocketBase using provided credentials |
| list_documentsC | List stored documents from PocketBase with pagination |
| search_documentsB | Search documents by title or content using full-text search |
| get_documentB | Get a specific document by ID with full content |
| delete_documentB | Delete a document from PocketBase by ID |
| ensure_collectionA | Check if the documents collection exists and create it if needed |
| collection_infoB | Get detailed information about the documents collection including statistics |
| connection_statusB | Check the current PocketBase connection status and configuration |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| stats | Current server statistics and metrics |
TDQS
Scored across 9 tools
Each tool has a clearly distinct purpose targeting specific operations: authentication, collection management, connection checks, CRUD operations (delete, get, list, search), and document extraction. No tools overlap in functionality, making selection straightforward for an agent.
All tool names follow a consistent verb_noun pattern (e.g., authenticate, collection_info, delete_document), with clear and descriptive naming. There are no deviations in style or convention across the set.
With 9 tools, the server is well-scoped for document extraction and management, covering authentication, setup, CRUD operations, and search. Each tool serves a necessary function without bloat or redundancy.
The toolset provides strong coverage for core document workflows: authentication, collection setup, extraction, retrieval, listing, searching, and deletion. A minor gap exists in update functionality (e.g., update_document), but agents can work around this by deleting and re-extracting.