Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DB_PATHNoPath to the LanceDB index. If empty, uses <project>/index.lance.
PDF_ROOTNoPath to the PDF/Markdown manuals root. If empty, uses <project>/pdf.
MCP_INPROCNoSet to 0 to run the MCP server as a separate process instead of the default in-process mode.
ADMIN_TOKENNoAdmin token for /api/admin/* endpoints. If empty, all such requests return 403.
EMBED_MODELNoEmbedding model name. Must match the model used at index build time.
OCR_API_KEYNoAPI key for remote OCR (if used). Read only from environment.
EMBED_API_KEYYesAPI key for the embedding service. Read only from environment, never stored in DB/packages/frontend.
EMBED_BASE_URLNoOpenAI-compatible /v1 base URL for the embedding service.
RERANKER_MODELNoReranker model name.
EMBED_DIMENSIONSNoEmbedding vector dimensions. Must match the index dimensions (currently 768).768

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

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