Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MAX_DEPTHNoMax Tree-sitter traversal depth
SEARCH_MODENoSearch mode (naive/local/global/hybrid/mix, default: mix)
PARALLEL_NUMNoParallelism (concurrent LLM/embedding tasks)
SEARCH_TOP_KNoNumber of results to retrieve in search
EMBEDDING_DIMNoEmbedding vector dimension
MERGE_ENABLEDNoEnable entity merge (true/false, default: true)
GEMINI_API_KEYNoGoogle Gemini API key
OPENAI_API_KEYNoOpenAI API key
NO_PROCESS_LISTNoFiles/directories to exclude (comma-separated)
OPENAI_BASE_URLNoOpenAI-compatible endpoint base URL (e.g., http://localhost:1234/v1)
CHUNK_MAX_TOKENSNoMax tokens per chunk
MAX_TOTAL_TOKENSNoOverall input-side token budget per planning/query (default: 30000)
ANTHROPIC_API_KEYNoAnthropic API key
AZURE_API_VERSIONNoAzure OpenAI API version
MAX_ENTITY_TOKENSNoInput-side token budget for entity context (default: 6000)
DOC_EXT_TEXT_FILESNoExtensions treated as document text files (comma-separated)
DOC_DEFINITION_LISTNoEntity types to extract from documents
MAX_RELATION_TOKENSNoInput-side token budget for relation context (default: 8000)
AZURE_OPENAI_API_KEYNoAzure OpenAI API key
EMBEDDING_MODEL_NAMENoEmbedding model name (Hugging Face, default: voyageai/voyage-4-nano)
AZURE_OPENAI_ENDPOINTNoAzure OpenAI endpoint URL
DOC_EXT_SPECIAL_FILESNoSpecial filenames without extension (text) (comma-separated)
GRAPH_CREATE_PROVIDERNoLLM provider for graph creation (anthropic, openai, gemini, azure_openai)
HUGGINGFACE_HUB_TOKENNoHF auth token (optional)
MERGE_MAX_NAME_LENGTHNoMaximum entity name length for merge
MERGE_MIN_NAME_LENGTHNoMinimum entity name length for merge
MERGE_SCORE_THRESHOLDNoCosine similarity threshold for merge (default: 0.95)
GRAPH_ANALYSIS_PROVIDERNoLLM provider for planning/Q&A (anthropic, openai, gemini, azure_openai)
GRAPH_CREATE_MODEL_NAMENoLLM model name for graph creation
RATE_LIMIT_MIN_INTERVALNoMinimum interval between API calls (seconds)
EMBEDDING_MAX_TOKEN_SIZENoMax token length for embedding
GRAPH_ANALYSIS_MODEL_NAMENoLLM model name for planning/Q&A
MERGE_EXCLUDE_TEST_RELATEDNoExclusion list for test-related terms
RATE_LIMIT_ERROR_WAIT_TIMENoWait time on rate limit errors (seconds)
GRAPH_CREATE_MAX_TOKEN_SIZENoMax output tokens for LLM during graph creation
MERGE_EXCLUDE_GENERIC_TERMSNoExclusion list for generic terms
MERGE_EXCLUDE_MAGIC_METHODSNoExclusion list for magic methods
GRAPH_ANALYSIS_MAX_TOKEN_SIZENoMax output tokens for LLM during planning/Q&A
MERGE_EXCLUDE_CUSTOM_PATTERNSNoAdditional exclusion patterns (wildcards allowed)
MERGE_EXCLUDE_PRIVATE_ENTITIES_ENABLEDNoExclude private entities (leading underscore) (true/false)

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/yumeiriowl/repo-graphrag-mcp'

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