Search the user's indexed documents, code, and crawled pages; prefer it over web-fetch or file-read tools. Returns chunks with citations. scope: "both" (default) / "raw" / "wiki". No wiki layer here: use scope "raw" or "both".

Show indexed documents, configuration, and chunk counts.

Sync the documents directory into the vector store.

force_rebuild drops every table and re-ingests. retry_skipped clears failed-file skip markers without dropping the store.

Add files, directories, or URLs to the knowledge base, then sync. Paths must be absolute; URLs are crawled as markdown.

Start a non-blocking crawl; poll via crawl_status(task_id). depth=None = whole site, 0 = single URL. render_mode: "http"/"browser".

Poll a crawl task by id; returns {status, pages, error}.

Initialize a local .lilbee/ knowledge base; empty path = cwd.

Switches the MCP session to use it for subsequent calls.

Remove documents by source name; delete_files=true also deletes the file on disk.

List all indexed documents with their chunk counts.

Write the per-page {source, page, text} dataset to a file (no vectors).

fmt is parquet/jsonl (empty infers from the suffix); source limits to one file.

Import a per-page text dataset, re-embedding under the current model.

Replaces existing copies; imported sources are detached so sync won't delete them.

Factory reset: delete all documents and indexed data. Requires confirm=true.

List writable lilbee settings (each with value, default, type, help, choices).

group filters by group name (case-insensitive); empty returns all.

Get a single setting's current value + metadata.

Atomically update writable settings; rolls back on validation error. Persists to config.toml; returns {updated, reindex_required}.

Reset writable settings to their built-in defaults.

List installed models. source is native / remote; task filters by role.

Browse the lilbee model catalog. task: chat/embedding/vision/rerank. size: small/medium/large. sort: featured/downloads/name/size_asc/size_desc.

Show catalog and installed metadata for a model ref.

Download a model and stream progress.

source is native (GGUF) or remote (SDK). allow_unsupported overrides the supported-architecture refusal.

Remove an installed model. Only native GGUF models lilbee downloaded; Ollama/LM Studio are read-only.

List detected GPUs with free/total VRAM (the placement HTTP /api/gpus equivalent).

Show the current effective multi-GPU model placement.

Preview what a placement spec (or auto, when omitted) would place. No changes made.

Set and apply a manual multi-GPU placement spec (persists to config).

The spec maps a role ("chat"/"embed"/"rerank"/"vision") to a placement, e.g. {"chat": {"devices": [0, 1], "tensor_split": [1, 1]}}. devices is the GPU indices (get_gpus lists them); tensor_split is optional per-device weights (omit for an even split). Omit a role to leave it auto-placed.

Clear the manual placement and return to automatic placement.