KaaS
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | Model name. | gpt-4o-mini |
| KAAS_KB_DIR | No | The knowledge-base root directory (required for stdio transport). | |
| LLM_API_KEY | No | OpenAI-compatible API key. | |
| KAAS_WEB_DIR | No | Web directory path (default /app/web/dist in Docker). | |
| LLM_BASE_URL | No | API endpoint for the LLM. | https://api.openai.com/v1 |
| KAAS_MCP_TOKEN | No | Bearer token for MCP auth (empty = no auth). Optional for streamable-http. | |
| KAAS_AI_MCP_URL | No | Deprecated — use KAAS_MCP_ENABLED instead. | |
| KAAS_MCP_ENABLED | No | Set to "true" to expose the /mcp endpoint (required for streamable-http transport). | false |
| LLM_SUMMARIZE_MODEL | No | Model to use for summarization (defaults to LLM_MODEL). | |
| KB_AI_WRITE_TIMEOUT_S | No | Timeout in seconds for write phase. | 300 |
| KB_AI_EXTRACT_TIMEOUT_S | No | Timeout in seconds for extract phase. | 180 |
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
ActivityMaintained
ResponsivenessResponsive