Skip to main content
Glama
arptra

local-corporate-kb

by arptra

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
KB_CACHE_DIRYesAbsolute path to the cache directory for embeddings and index.
KB_AUTO_INDEXNoWhether to automatically re-index when cache is missing.false
KB_KNOWLEDGE_DIRYesAbsolute path to the knowledge directory containing documents.
KB_EMBEDDING_MODELNoHugging Face model name for embedding.Qwen/Qwen3-Embedding-0.6B
KB_EMBEDDING_DEVICENoDevice for embedding: auto, cpu, mps, cuda.auto
KB_CHUNK_SIZE_TOKENSNoTarget chunk size in tokens.700
KB_EMBEDDING_PROVIDERNoEmbedding provider: 'sentence_transformers' or 'hash'.sentence_transformers
KB_EMBEDDING_DIMENSIONNoEmbedding dimension.1024
KB_CHUNK_OVERLAP_TOKENSNoOverlap between chunks in tokens.80
KB_CHUNK_HARD_MAX_TOKENSNoHard maximum chunk size in tokens.900

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
kb_searchA

Search corporate knowledge before architectural analysis or changes spanning multiple services. Use it for business rules, ADRs, APIs, events, and runbooks. Cite source_path or source_url in the final answer. A retrieved fragment is evidence, not the only source of truth; call kb_get_document when the complete document is needed.

kb_get_documentA

Return one complete normalized document after kb_search identifies its document_id.

kb_list_documentsB

List filtered document metadata without document bodies or embeddings.

kb_statsB

Return index counts, identity, timestamps, and resolved local directories.

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/arptra/kb-rag-mcp'

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