KaaS
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | Model name. Default gpt-4o-mini | gpt-4o-mini |
| KAAS_KB_DIR | No | Knowledge-base root directory for the stdio MCP server (required for the stdio transport). | |
| LLM_API_KEY | No | OpenAI-compatible API key. Default empty. | |
| LLM_BASE_URL | No | API endpoint. Default https://api.openai.com/v1 | https://api.openai.com/v1 |
| KAAS_MCP_TOKEN | No | Bearer token for MCP auth on the HTTP transport. Empty means no auth. | |
| KAAS_MCP_ENABLED | No | Set to true to expose the /mcp endpoint for streamable-http MCP access. Default false. | false |
| LLM_SUMMARIZE_MODEL | No | Model for summarization. Defaults to same as LLM_MODEL. | |
| KB_AI_WRITE_TIMEOUT_S | No | Timeout in seconds for write phase. Default 300. | 300 |
| KB_AI_EXTRACT_TIMEOUT_S | No | Timeout in seconds for extract phase. Default 180. | 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
ActivityActive
ResponsivenessResponsive