Saga
by maxinedotdev
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_AI_MODEL | No | AI model name | |
| MCP_BASE_DIR | No | Base directory for data storage | ~/.saga |
| MCP_HTTP_HOST | No | HTTP host for httpStream transport | 127.0.0.1 |
| MCP_HTTP_PORT | No | HTTP port for httpStream transport | 8080 |
| MCP_TRANSPORT | No | Transport mode: stdio or httpStream | stdio |
| MCP_AI_API_KEY | No | API key for AI provider | |
| MCP_AI_BASE_URL | No | Base URL for AI provider (enables search_documents_with_ai) | |
| MCP_HTTP_PUBLIC | No | Set to 'true' to bind to 0.0.0.0 (public) | |
| MCP_LOG_TO_FILE | No | Set to 'true' to enable file logging to ~/.saga/logs/ | |
| MCP_HTTP_ENDPOINT | No | HTTP endpoint for httpStream transport | /mcp |
| MCP_HTTP_STATELESS | No | HTTP stateless mode (set 'false' for session mode) | true |
| MCP_EMBEDDING_MODEL | No | Embedding model name | |
| MCP_EMBEDDING_BASE_URL | Yes | Required: Base URL for the embedding API |
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
ActivityInactive
ResponsivenessSyncing