Skip to main content
Glama
renefichtmueller

PaperCortex

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_PORTNoPort for HTTP transport mode3100
BATCH_SIZENoNumber of documents to process per batch10
EXPORT_DIRNoDirectory for generated export files./exports
OLLAMA_URLNoOllama API endpointhttp://localhost:11434
OLLAMA_MODELNoLLM model for classification and extractionqwen2.5:14b
MCP_TRANSPORTNoMCP transport mode (stdio or http)stdio
PAPERLESS_URLNoPaperless-ngx instance URLhttp://localhost:8000
POLL_INTERVALNoSeconds between polling Paperless-ngx for new documents300
MCP_AUTH_TOKENNoBearer token for HTTP transport authentication
VECTOR_DB_PATHNoPath to the SQLite vector database./data/vectors.db
PAPERLESS_TOKENYesPaperless-ngx API authentication token
DATEV_CLIENT_NUMBERNoMandantennummer for DATEV export header
DATEV_ADVISOR_NUMBERNoSteuerberater number for DATEV export header
DEFAULT_ACCOUNT_PLANNoDefault chart of accounts (SKR03 or SKR04)SKR03
EMBEDDING_DIMENSIONSNoVector dimensions (must match embedding model)768
OLLAMA_EMBEDDING_MODELNoEmbedding model for semantic searchnomic-embed-text
DATEV_FISCAL_YEAR_STARTNoFiscal year start (MM-DD)01-01
CLASSIFICATION_CONFIDENCENoMinimum confidence to auto-apply classifications0.7

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

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