Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
NO_COLORNoIf set, disables ANSI colors in terminal
CRG_TOOLSNoComma-separated allowlist of MCP tools to expose when serving
PYTHONUTF8NoSet to '1' to force UTF-8 encoding on Windows (see Windows Configuration Issues)
CRG_DATA_DIRNoOverride directory for graph databases and generated graph artefacts
GOOGLE_API_KEYNoAPI key for Google Gemini embeddings
VOYAGE_API_KEYNoAPI key for Voyage embeddings
CRG_GIT_TIMEOUTNoTimeout in seconds for Git operations30
MINIMAX_API_KEYNoAPI key for MiniMax embeddings
CRG_OPENAI_MODELNoModel name for OpenAI-compatible embeddings
CRG_SERIAL_PARSENoIf '1', disables parallel parsing (use for debugging)
CRG_TOOL_TIMEOUTNoOptional timeout in seconds for bounded MCP tools (0 disables timeout)0
CRG_VOYAGE_MODELNoModel name for Voyage embeddingsvoyage-code-3
CRG_MAX_BFS_DEPTHNoMaximum depth for graph traversal15
CRG_OPENAI_API_KEYNoAPI key for OpenAI-compatible embeddings
CRG_EMBEDDING_MODELNoDefault model for vector embeddingsall-MiniLM-L6-v2
CRG_OPENAI_BASE_URLNoOpenAI-compatible embeddings endpoint
CRG_VOYAGE_BASE_URLNoVoyage embeddings endpointhttps://api.voyageai.com/v1
CRG_MAX_IMPACT_DEPTHNoSearch depth for blast-radius analysis2
CRG_MAX_IMPACT_NODESNoMaximum nodes to include in impact analysis500
CRG_OPENAI_DIMENSIONNoPin embedding dimension (v3 models support reduction)
CRG_ALLOW_REMOTE_CODENoAllow HuggingFace models that require 'trust_remote_code=True'0
CRG_MAX_CHANGED_FUNCSNoMaximum changed functions analysed in one change report500
CRG_OPENAI_BATCH_SIZENoBatch size for OpenAI-compatible embedding requests (lower for gateways with tight limits)
CRG_VOYAGE_BATCH_SIZENoBatch size for Voyage embedding requests100
CRG_RECURSE_SUBMODULESNoInclude git submodules in file collection when set to '1', 'true', or 'yes'
CRG_VOYAGE_OUTPUT_DTYPENoOutput dtype for Voyage embeddingsfloat
CRG_ACCEPT_CLOUD_EMBEDDINGSNoSuppress the cloud embedding egress warning after explicit acknowledgement
CRG_MAX_TRANSITIVE_FRONTIERNoMaximum frontier size for transitive caller/callee expansion50
CRG_VOYAGE_MIN_INTERVAL_SECNoMinimum delay between Voyage requests0
CRG_VOYAGE_OUTPUT_DIMENSIONNoOutput dimension for Voyage embeddings1024

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/es-3581100/code-review-graph'

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