KaaS
by dTsipras7651
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | Model name (overrides [llm] model). | gpt-4o-mini |
| KAAS_KB_DIR | No | Knowledge-base root directory. Required for the stdio transport (kb-ai mcp). | |
| LLM_API_KEY | No | OpenAI-compatible API key. Required to call the LLM (overrides [llm] api_key in kaas.toml). | |
| LLM_BASE_URL | No | 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 (overrides [ai.mcp] token). Empty = no auth. | |
| KAAS_MCP_ENABLED | No | Set to true to expose the remote /mcp endpoint through the backend (overrides [ai.mcp] enabled). Default false. | |
| LLM_SUMMARIZE_MODEL | No | Model used for summarization; defaults to the same as model (overrides [llm] summarize_model). | |
| KB_AI_WRITE_TIMEOUT_S | No | Per-attempt write phase timeout in seconds (env only). Raise for slow local models. | 300 |
| KB_AI_EXTRACT_TIMEOUT_S | No | Per-attempt extract phase timeout in seconds (env only). Size conservatively for slow local models. | 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