KaaS
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | Model name. Overrides `[llm] model` in kaas.toml. | gpt-4o-mini |
| KAAS_KB_DIR | Yes | The knowledge-base root directory. Set this in the environment when the agent launches the stdio MCP server (`kb-ai mcp`). | |
| LLM_API_KEY | Yes | OpenAI-compatible API key. Overrides `[llm] api_key` in kaas.toml. | |
| LLM_BASE_URL | No | OpenAI-compatible API endpoint. Overrides `[llm] base_url` in kaas.toml. | https://api.openai.com/v1 |
| KAAS_MCP_TOKEN | No | Bearer token required as `Authorization: Bearer <token>` on the HTTP MCP transport (empty = no auth). Overrides `[ai.mcp] token`. | |
| KAAS_MCP_ENABLED | No | Set to true to expose the remote streamable-http MCP endpoint at /mcp from the backend. Overrides `[ai.mcp] enabled`. | false |
| LLM_SUMMARIZE_MODEL | No | Model used for summarization. Overrides `[llm] summarize_model` in kaas.toml. | same as model |
| KB_AI_WRITE_TIMEOUT_S | No | Timeout in seconds for the compile write phase (env only). Raise when compiling with a slow local model. | 300 |
| KB_AI_EXTRACT_TIMEOUT_S | No | Timeout in seconds for the extract phase (env only). Size more conservatively than the write 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
ActivityActive
ResponsivenessNo issues