Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
SOPHON_HYBRIDNoSet to '1' to enable BM25 sparse-lexical + HashEmbedder fused via RRF.
SOPHON_LLM_CMDNoLLM shell-out command (e.g., 'claude -p --model haiku') used by summarizer when configured.
SOPHON_EMBEDDERNoEmbedder to use (e.g., 'bge' to swap HashEmbedder for BGE-small, requires --features bge build).
SOPHON_MEMORY_PATHNoPath to JSONL file for persistent conversation memory across server runs.
SOPHON_CHUNK_TARGETNoTarget chunk size in tokens (e.g., '500'). Larger chunks preserve cross-sentence context.
SOPHON_RETRIEVER_PATHNoPath to directory for semantic retriever (chunk store on disk). Activates the retriever.
SOPHON_ROLLING_SUMMARYNoSet to '1' to build rolling summary at update_memory time instead of query time.

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/lacausecrypto/mcp-sophon'

If you have feedback or need assistance with the MCP directory API, please join our Discord server