PaperCortex
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_PORT | No | Port for HTTP transport mode | 3100 |
| BATCH_SIZE | No | Number of documents to process per batch | 10 |
| EXPORT_DIR | No | Directory for generated export files | ./exports |
| OLLAMA_URL | No | Ollama API endpoint | http://localhost:11434 |
| OLLAMA_MODEL | No | LLM model for classification and extraction | qwen2.5:14b |
| MCP_TRANSPORT | No | MCP transport mode (stdio or http) | stdio |
| PAPERLESS_URL | No | Paperless-ngx instance URL | http://localhost:8000 |
| POLL_INTERVAL | No | Seconds between polling Paperless-ngx for new documents | 300 |
| MCP_AUTH_TOKEN | No | Bearer token for HTTP transport authentication | |
| VECTOR_DB_PATH | No | Path to the SQLite vector database | ./data/vectors.db |
| PAPERLESS_TOKEN | Yes | Paperless-ngx API authentication token | |
| DATEV_CLIENT_NUMBER | No | Mandantennummer for DATEV export header | |
| DATEV_ADVISOR_NUMBER | No | Steuerberater number for DATEV export header | |
| DEFAULT_ACCOUNT_PLAN | No | Default chart of accounts (SKR03 or SKR04) | SKR03 |
| EMBEDDING_DIMENSIONS | No | Vector dimensions (must match embedding model) | 768 |
| OLLAMA_EMBEDDING_MODEL | No | Embedding model for semantic search | nomic-embed-text |
| DATEV_FISCAL_YEAR_START | No | Fiscal year start (MM-DD) | 01-01 |
| CLASSIFICATION_CONFIDENCE | No | Minimum confidence to auto-apply classifications | 0.7 |
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 | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/renefichtmueller/PaperCortex'
If you have feedback or need assistance with the MCP directory API, please join our Discord server