code-review-graph
by es-3581100
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NO_COLOR | No | If set, disables ANSI colors in terminal | |
| CRG_TOOLS | No | Comma-separated allowlist of MCP tools to expose when serving | |
| PYTHONUTF8 | No | Set to '1' to force UTF-8 encoding on Windows (see Windows Configuration Issues) | |
| CRG_DATA_DIR | No | Override directory for graph databases and generated graph artefacts | |
| GOOGLE_API_KEY | No | API key for Google Gemini embeddings | |
| VOYAGE_API_KEY | No | API key for Voyage embeddings | |
| CRG_GIT_TIMEOUT | No | Timeout in seconds for Git operations | 30 |
| MINIMAX_API_KEY | No | API key for MiniMax embeddings | |
| CRG_OPENAI_MODEL | No | Model name for OpenAI-compatible embeddings | |
| CRG_SERIAL_PARSE | No | If '1', disables parallel parsing (use for debugging) | |
| CRG_TOOL_TIMEOUT | No | Optional timeout in seconds for bounded MCP tools (0 disables timeout) | 0 |
| CRG_VOYAGE_MODEL | No | Model name for Voyage embeddings | voyage-code-3 |
| CRG_MAX_BFS_DEPTH | No | Maximum depth for graph traversal | 15 |
| CRG_OPENAI_API_KEY | No | API key for OpenAI-compatible embeddings | |
| CRG_EMBEDDING_MODEL | No | Default model for vector embeddings | all-MiniLM-L6-v2 |
| CRG_OPENAI_BASE_URL | No | OpenAI-compatible embeddings endpoint | |
| CRG_VOYAGE_BASE_URL | No | Voyage embeddings endpoint | https://api.voyageai.com/v1 |
| CRG_MAX_IMPACT_DEPTH | No | Search depth for blast-radius analysis | 2 |
| CRG_MAX_IMPACT_NODES | No | Maximum nodes to include in impact analysis | 500 |
| CRG_OPENAI_DIMENSION | No | Pin embedding dimension (v3 models support reduction) | |
| CRG_ALLOW_REMOTE_CODE | No | Allow HuggingFace models that require 'trust_remote_code=True' | 0 |
| CRG_MAX_CHANGED_FUNCS | No | Maximum changed functions analysed in one change report | 500 |
| CRG_OPENAI_BATCH_SIZE | No | Batch size for OpenAI-compatible embedding requests (lower for gateways with tight limits) | |
| CRG_VOYAGE_BATCH_SIZE | No | Batch size for Voyage embedding requests | 100 |
| CRG_RECURSE_SUBMODULES | No | Include git submodules in file collection when set to '1', 'true', or 'yes' | |
| CRG_VOYAGE_OUTPUT_DTYPE | No | Output dtype for Voyage embeddings | float |
| CRG_ACCEPT_CLOUD_EMBEDDINGS | No | Suppress the cloud embedding egress warning after explicit acknowledgement | |
| CRG_MAX_TRANSITIVE_FRONTIER | No | Maximum frontier size for transitive caller/callee expansion | 50 |
| CRG_VOYAGE_MIN_INTERVAL_SEC | No | Minimum delay between Voyage requests | 0 |
| CRG_VOYAGE_OUTPUT_DIMENSION | No | Output dimension for Voyage embeddings | 1024 |
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/es-3581100/code-review-graph'
If you have feedback or need assistance with the MCP directory API, please join our Discord server