KaaS
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | The model name. Overrides `[llm] model`. | gpt-4o-mini |
| KAAS_KB_DIR | No | The knowledge-base root directory. Set this when running the stdio MCP server (`kb-ai mcp`) so the agent can locate the compiled wiki. | |
| LLM_API_KEY | Yes | OpenAI-compatible API key. Overrides `[llm] api_key`. | |
| LLM_BASE_URL | No | The OpenAI-compatible API endpoint. Overrides `[llm] base_url`. | https://api.openai.com/v1 |
| KAAS_MCP_TOKEN | No | Bearer token required on the HTTP MCP transport (`Authorization: Bearer <token>`). Empty = no auth. Overrides `[ai.mcp] token`. | |
| KAAS_MCP_ENABLED | No | Set true to expose the remote MCP endpoint at `/mcp`. Overrides `[ai.mcp] enabled`. | false |
| LLM_SUMMARIZE_MODEL | No | Model used for summarization. Overrides `[llm] summarize_model`. Defaults to the value of `LLM_MODEL`. | |
| KB_AI_WRITE_TIMEOUT_S | No | Timeout in seconds for the write phase of compilation (env only). | 300 |
| KB_AI_EXTRACT_TIMEOUT_S | No | Timeout in seconds for the extract phase of compilation (env only). | 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
ResponsivenessNo issues