SAGE-MCP
by david-strejc
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| REDIS_DB | No | Redis database number | 0 |
| REDIS_URL | No | Redis connection for memory | redis://localhost:6379/0 |
| XAI_API_KEY | No | xAI (Grok) API key | |
| DEFAULT_MODEL | No | Default model (auto for automatic selection) | auto |
| MAX_FILE_SIZE | No | Maximum file size in bytes (5MB) | 5242880 |
| ALLOWED_MODELS | No | Comma-separated list of allowed models | |
| BLOCKED_MODELS | No | Blocked models (any provider) | |
| CUSTOM_API_KEY | No | Custom API key (if required) | |
| CUSTOM_API_URL | No | Custom/Ollama API endpoint | |
| FALLBACK_MODEL | No | Fallback model for errors | |
| GEMINI_API_KEY | No | Google Gemini API key | |
| GOOGLE_API_KEY | No | Google Gemini API key (alternative name) | |
| OPENAI_API_KEY | No | OpenAI API key | |
| DEFAULT_PROVIDER | No | Default AI provider | auto |
| MAX_TOKENS_GPT4O | No | Maximum tokens for GPT-4O | 128000 |
| TEMPERATURE_CHAT | No | Chat mode temperature | 0.5 |
| TEMPERATURE_PLAN | No | Plan mode temperature | 0.4 |
| TEMPERATURE_TEST | No | Test mode temperature | 0.2 |
| ANTHROPIC_API_KEY | No | Anthropic Claude API key | |
| DISALLOWED_MODELS | No | Comma-separated list of disallowed models | |
| MAX_TOKENS_CLAUDE | No | Maximum tokens for Claude | 200000 |
| TEMPERATURE_DEBUG | No | Debug mode temperature | 0.1 |
| TEMPERATURE_THINK | No | Think mode temperature | 0.7 |
| WEBSEARCH_ENABLED | No | Enable web search | true |
| OPENROUTER_API_KEY | No | OpenRouter API key | |
| TEMPERATURE_REVIEW | No | Review mode temperature | 0.3 |
| FILE_SECURITY_CHECK | No | Validate file paths | true |
| TEMPERATURE_ANALYZE | No | Analyze mode temperature | 0.2 |
| AUTO_MODEL_SELECTION | No | Smart model selection | true |
| TEMPERATURE_REFACTOR | No | Refactor mode temperature | 0.3 |
| GOOGLE_ALLOWED_MODELS | No | Allowed Google models | |
| MCP_PROMPT_SIZE_LIMIT | No | MCP transport limit | 50000 |
| OPENAI_ALLOWED_MODELS | No | Allowed OpenAI models | |
| MAX_CONVERSATION_TURNS | No | Maximum turns per conversation | 20 |
| MAX_THINKING_TOKENS_O1 | No | Maximum thinking tokens for O1 | 100000 |
| DISABLED_MODEL_PATTERNS | No | Disable models by pattern | |
| ANTHROPIC_ALLOWED_MODELS | No | Allowed Anthropic models | |
| CONVERSATION_TIMEOUT_HOURS | No | Conversation timeout in hours | 3 |
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/david-strejc/sage-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server