kb
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KB_DB_PATH | No | Where the SQLite index database lives. | ~/.local/share/kb/index.db |
| GEMINI_MODEL | No | Model used for generation. | gemini-2.5-flash |
| GEMINI_API_KEY | No | API key for Gemini. Required for 'ask'/'digest' tools or when using the Gemini embeddings backend. | |
| KB_CONFIG_PATH | No | Path to the TOML configuration file (sources, digest questions). | kb.toml |
| EMBEDDINGS_BACKEND | No | Backend for embeddings: 'local' (offline, no cost) or 'gemini' (requires GEMINI_API_KEY). | local |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_knowledge_baseA | Busqueda semantica en la base local. Devuelve los fragmentos mas relevantes con su ruta de archivo y un score de similitud (0-1). No usa LLM. |
| ask_knowledge_baseA | Responde una pregunta con RAG sobre la base local: recupera contexto y genera una respuesta con Gemini, citando los archivos fuente. Necesita GEMINI_API_KEY configurada. |
| reindex_knowledge_baseA | Re-indexa (incremental) las carpetas configuradas en kb.toml. Solo procesa lo que cambio desde la ultima corrida. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
The three tools are clearly distinct: search returns raw fragments, ask generates an LLM answer with citations, and reindex refreshes the index. The only minor overlap is that search and ask both retrieve from the knowledge base, but their outputs and purposes are different enough.
All tool names follow a consistent verb_noun pattern: search_knowledge_base, ask_knowledge_base, reindex_knowledge_base. The verbs are distinct and the object is consistent, making the pattern predictable.
Three tools is a reasonable, focused set for a knowledge base server. It covers the core operations (search, ask, reindex) without unnecessary bloat, though it is on the smaller side.
The core operations are covered: retrieval, RAG-based Q&A, and index maintenance. However, there is no tool to add, update, or delete documents directly, and no way to inspect the index status or configuration, which could be a gap depending on the intended workflow.