Graphify
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | No | Google Gemini API key, used for semantic extraction when the Gemini backend is selected/auto-detected. | |
| GOOGLE_API_KEY | No | Google API key (alternative to GEMINI_API_KEY) for Gemini-based semantic extraction. | |
| OPENAI_API_KEY | No | OpenAI (or OpenAI-compatible) API key, used with --backend openai. | |
| ANTHROPIC_MODEL | No | Custom model for the Anthropic-compatible endpoint used with the claude backend. | |
| OLLAMA_BASE_URL | No | Base URL of a running Ollama instance for fully local inference (--backend ollama). | |
| DEEPSEEK_API_KEY | No | DeepSeek API key for semantic extraction. | |
| GRAPHIFY_BACKEND | No | Explicitly choose the LLM backend (e.g. gemini, kimi, claude, openai, deepseek, azure, bedrock, ollama, none). When unset, graphify auto-detects based on which API key is set (priority: Gemini → Kimi → Claude → OpenAI → DeepSeek → Azure → Bedrock → Ollama). Set to 'none' to disable all LLM backends and keep a code-only graph. | |
| MOONSHOT_API_KEY | No | Moonshot AI (Kimi) API key. Note: routes to Moonshot AI servers in China. | |
| ANTHROPIC_API_KEY | No | Anthropic Claude API key, used with --backend claude. | |
| ANTHROPIC_BASE_URL | No | Custom base URL for the Anthropic-compatible endpoint used with the claude backend. | |
| GRAPHIFY_QUERY_LOG | No | Path to the query log file. Set to /dev/null to silence logging without disabling the code path. | |
| AZURE_OPENAI_API_KEY | No | Azure OpenAI Service API key, used with --backend azure. | |
| GRAPHIFY_HOOK_STRICT | No | Set to '1' to enable once-per-session denial of reads against an indexed (fresh/non-stale) graph via the hook. | |
| AZURE_OPENAI_ENDPOINT | No | Azure OpenAI Service endpoint, used with --backend azure. | |
| GRAPHIFY_VIZ_NODE_LIMIT | No | Node limit for aggregated community visualization; applies to cluster-only, update, watch, and hooks. | |
| GRAPHIFY_CLAUDE_CLI_MODEL | No | Overrides the model for the claude-cli backend (default: Opus). | |
| GRAPHIFY_QUERY_LOG_DISABLE | No | Set to '1' to opt out of query logging to ~/.cache/graphify-queries.log. | |
| GRAPHIFY_CLAUDE_PROMPT_CACHE | No | Controls system-prompt caching for the claude backend. Unset or blank keeps caching enabled; '1', 'true', 'yes', or 'on' enables it; '0', 'false', 'no', or 'off' disables it (case-insensitive). Invalid values raise an error before sending a request. |
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 | |
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessResponsive