Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HTTP_PORTNoPort for the utility HTTP server. Can also be specified via --port CLI argument.3001
LOG_LEVELNoLogging level (e.g., error, warn, info, verbose, debug, silly).info
OLLAMA_HOSTNoURL for the Ollama server.http://localhost:11434
QDRANT_HOSTNoURL for the Qdrant vector store server.http://localhost:6333
LLM_PROVIDERNoSpecifies the primary LLM provider for generating suggestions. Supported values: ollama, deepseek, openai, gemini, claude.ollama
CLAUDE_API_KEYNoYour API key for Anthropic Claude (required if LLM_PROVIDER=claude).
GEMINI_API_KEYNoYour API key for Google Gemini (required if LLM_PROVIDER=gemini).
OPENAI_API_KEYNoYour API key for OpenAI (required if LLM_PROVIDER=openai).
COLLECTION_NAMENoName of the Qdrant collection for this repository.
EMBEDDING_MODELNoThe specific model to use for embeddings via Ollama.nomic-embed-text:v1.5
DEEPSEEK_API_KEYNoYour API key for DeepSeek (required if LLM_PROVIDER=deepseek).
DEEPSEEK_API_URLNoCustom API URL for DeepSeek if not using the default.https://api.deepseek.com/chat/completions
REFINEMENT_MODELNoLLM model to use for query refinement. Defaults to SUGGESTION_MODEL if not set.
SUGGESTION_MODELNoThe specific model to use for suggestions.llama3.1:8b
DEEPSEEK_RPM_LIMITNoRequests per minute limit for DeepSeek.20
EMBEDDING_PROVIDERNoProvider for generating embeddings. Currently ollama is supported.ollama
AGENT_QUERY_TIMEOUTNoTimeout in milliseconds for agent's LLM reasoning steps.180000
SUMMARIZATION_MODELNoLLM model to use for summarization tasks. Defaults to SUGGESTION_MODEL if not set.
AGENT_DEFAULT_MAX_STEPSNoDefault maximum number of steps the agent will take.10
AGENT_ABSOLUTE_MAX_STEPSNoAbsolute maximum number of steps the agent can take.15
MAX_REFINEMENT_ITERATIONSNoMaximum number of iterations for query refinement.3
QDRANT_SEARCH_LIMIT_DEFAULTNoDefault number of results to fetch from Qdrant during standard searches.10
FILE_INDEXING_CHUNK_SIZE_CHARSNoTarget size for chunks when indexing large files (in characters).1000
MAX_DIFF_LENGTH_FOR_CONTEXT_TOOLNoMaximum length of a git diff to include in context without summarization.3000
FILE_INDEXING_CHUNK_OVERLAP_CHARSNoOverlap between chunks when indexing large files (in characters).200
MAX_SNIPPET_LENGTH_FOR_CONTEXT_NO_SUMMARYNoMaximum length of a code snippet to include in context without summarization.1500
MAX_FILES_FOR_SUGGESTION_CONTEXT_NO_SUMMARYNoMaximum number of files to list directly in the generate_suggestion tool's context before summarizing.15
REQUEST_ADDITIONAL_CONTEXT_MAX_SEARCH_RESULTSNoNumber of search results to fetch when agent uses request_additional_context.20

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/alvinveroy/CodeCompass'

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