Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HTTP_PORTNoPort for HTTP transport3000
LOG_LEVELNoLogging level: fatal, error, warn, info, debug, trace, silentinfo
QDRANT_URLNoQdrant server URLhttp://localhost:6333
GIT_TIMEOUTNoTimeout for git commands in milliseconds300000
COHERE_API_KEYNoCohere API key (required if using Cohere provider)
GIT_BATCH_SIZENoNumber of chunks to embed in one batch100
OPENAI_API_KEYNoOpenAI API key (required if using OpenAI provider)
QDRANT_API_KEYNoAPI key for Qdrant authentication (required for secured instances)
TRANSPORT_MODENoTransport mode: 'stdio' or 'http'stdio
VOYAGE_API_KEYNoVoyage AI API key (required if using Voyage provider)
CODE_BATCH_SIZENoNumber of chunks to embed in one batch100
CODE_CHUNK_SIZENoMaximum chunk size in characters for code vectorization2500
CODE_ENABLE_ASTNoEnable AST-aware chunking (tree-sitter): 'true' or 'false'true
EMBEDDING_MODELNoEmbedding model name (provider-specific default)
GIT_MAX_COMMITSNoMaximum commits to index per run5000
GIT_INCLUDE_DIFFNoInclude truncated diff in chunks: 'true' or 'false'true
GIT_SEARCH_LIMITNoDefault search result limit10
GIT_ENABLE_HYBRIDNoEnable hybrid search with sparse vectors: 'true' or 'false'true
GIT_INCLUDE_FILESNoInclude changed file list in chunks: 'true' or 'false'true
GIT_MAX_DIFF_SIZENoMaximum diff size in bytes per commit5000
CODE_CHUNK_OVERLAPNoOverlap between chunks in characters300
CODE_CUSTOM_IGNORENoAdditional ignore patterns (comma-separated)
CODE_DEFAULT_LIMITNoDefault search result limit for code search5
EMBEDDING_BASE_URLNoCustom API URL for embedding provider
EMBEDDING_PROVIDERNoEmbedding provider: 'ollama', 'openai', 'cohere', or 'voyage'ollama
GIT_MAX_CHUNK_SIZENoMaximum characters per chunk3000
PROMPTS_CONFIG_FILENoPath to prompts configuration JSONprompts.json
EMBEDDING_RETRY_DELAYNoInitial retry delay in milliseconds1000
CODE_CUSTOM_EXTENSIONSNoAdditional file extensions (comma-separated)
HTTP_REQUEST_TIMEOUT_MSNoRequest timeout for HTTP transport in milliseconds300000
EMBEDDING_RETRY_ATTEMPTSNoRetry count for embedding requests3
GIT_BATCH_RETRY_ATTEMPTSNoRetry attempts for failed batches3
EMBEDDING_MAX_REQUESTS_PER_MINUTENoRate limit for embedding requests per minute

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

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/deveyus/qdrant-mcp-server'

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