KaaS
by Rainer51777
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | Model name used for retrieval and answering. | gpt-4o-mini |
| KAAS_KB_DIR | No | Path to the knowledge-base root directory, used by the local stdio MCP server (`kb-ai mcp`). | |
| LLM_API_KEY | No | API key for the OpenAI-compatible LLM endpoint that the `ask` tool uses to retrieve and answer from the compiled wiki. | |
| LLM_BASE_URL | No | Base URL of the OpenAI-compatible LLM API endpoint. | https://api.openai.com/v1 |
| KAAS_MCP_TOKEN | No | Bearer token required on the streamable-http MCP transport (Authorization: Bearer <token>). Empty means no authentication. | |
| KAAS_MCP_ENABLED | No | Set to true to expose the remote streamable-http MCP endpoint at /mcp on the backend's :8080 origin. | false |
| LLM_SUMMARIZE_MODEL | No | Model used for summarization; defaults to the same value as LLM_MODEL. | |
| KB_AI_WRITE_TIMEOUT_S | No | Timeout in seconds for the write/compile phase. Raise it when compiling with a slow local model. | 300 |
| KB_AI_EXTRACT_TIMEOUT_S | No | Timeout in seconds for the extract phase, which runs on every document. | 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