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) |
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
| 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
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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