repo-graphrag-mcp
by yumeiriowl
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MAX_DEPTH | No | Max Tree-sitter traversal depth | |
| SEARCH_MODE | No | Search mode (naive/local/global/hybrid/mix, default: mix) | |
| PARALLEL_NUM | No | Parallelism (concurrent LLM/embedding tasks) | |
| SEARCH_TOP_K | No | Number of results to retrieve in search | |
| EMBEDDING_DIM | No | Embedding vector dimension | |
| MERGE_ENABLED | No | Enable entity merge (true/false, default: true) | |
| GEMINI_API_KEY | No | Google Gemini API key | |
| OPENAI_API_KEY | No | OpenAI API key | |
| NO_PROCESS_LIST | No | Files/directories to exclude (comma-separated) | |
| OPENAI_BASE_URL | No | OpenAI-compatible endpoint base URL (e.g., http://localhost:1234/v1) | |
| CHUNK_MAX_TOKENS | No | Max tokens per chunk | |
| MAX_TOTAL_TOKENS | No | Overall input-side token budget per planning/query (default: 30000) | |
| ANTHROPIC_API_KEY | No | Anthropic API key | |
| AZURE_API_VERSION | No | Azure OpenAI API version | |
| MAX_ENTITY_TOKENS | No | Input-side token budget for entity context (default: 6000) | |
| DOC_EXT_TEXT_FILES | No | Extensions treated as document text files (comma-separated) | |
| DOC_DEFINITION_LIST | No | Entity types to extract from documents | |
| MAX_RELATION_TOKENS | No | Input-side token budget for relation context (default: 8000) | |
| AZURE_OPENAI_API_KEY | No | Azure OpenAI API key | |
| EMBEDDING_MODEL_NAME | No | Embedding model name (Hugging Face, default: voyageai/voyage-4-nano) | |
| AZURE_OPENAI_ENDPOINT | No | Azure OpenAI endpoint URL | |
| DOC_EXT_SPECIAL_FILES | No | Special filenames without extension (text) (comma-separated) | |
| GRAPH_CREATE_PROVIDER | No | LLM provider for graph creation (anthropic, openai, gemini, azure_openai) | |
| HUGGINGFACE_HUB_TOKEN | No | HF auth token (optional) | |
| MERGE_MAX_NAME_LENGTH | No | Maximum entity name length for merge | |
| MERGE_MIN_NAME_LENGTH | No | Minimum entity name length for merge | |
| MERGE_SCORE_THRESHOLD | No | Cosine similarity threshold for merge (default: 0.95) | |
| GRAPH_ANALYSIS_PROVIDER | No | LLM provider for planning/Q&A (anthropic, openai, gemini, azure_openai) | |
| GRAPH_CREATE_MODEL_NAME | No | LLM model name for graph creation | |
| RATE_LIMIT_MIN_INTERVAL | No | Minimum interval between API calls (seconds) | |
| EMBEDDING_MAX_TOKEN_SIZE | No | Max token length for embedding | |
| GRAPH_ANALYSIS_MODEL_NAME | No | LLM model name for planning/Q&A | |
| MERGE_EXCLUDE_TEST_RELATED | No | Exclusion list for test-related terms | |
| RATE_LIMIT_ERROR_WAIT_TIME | No | Wait time on rate limit errors (seconds) | |
| GRAPH_CREATE_MAX_TOKEN_SIZE | No | Max output tokens for LLM during graph creation | |
| MERGE_EXCLUDE_GENERIC_TERMS | No | Exclusion list for generic terms | |
| MERGE_EXCLUDE_MAGIC_METHODS | No | Exclusion list for magic methods | |
| GRAPH_ANALYSIS_MAX_TOKEN_SIZE | No | Max output tokens for LLM during planning/Q&A | |
| MERGE_EXCLUDE_CUSTOM_PATTERNS | No | Additional exclusion patterns (wildcards allowed) | |
| MERGE_EXCLUDE_PRIVATE_ENTITIES_ENABLED | No | Exclude private entities (leading underscore) (true/false) |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
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