steve/kb
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases 18 Wiki Activity

Update README for v3.0.0 — add MCP server docs, updatenote, fix version refs

Browse Source 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Steve Cliff
2026-04-02 21:45:31 +01:00
parent e7136a4a20
commit 0dc3065979
1 changed files with 67 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+67 -3
View File
@@ -2,16 +2,19 @@
Personal knowledge base with hybrid search (full-text + semantic vector search).
v2 uses a client-server architecture: a **FastAPI engine** running in Docker (with optional GPU acceleration) and a lightweight **Go CLI client** that talks to it over HTTP.
Client-server architecture: a **FastAPI engine** running in Docker (with optional GPU acceleration), a lightweight **Go CLI client**, and an **MCP server** for native agent integration.
## Architecture
```
Go CLI (kb) ──HTTP──▶ FastAPI Engine (Docker) ──▶ SQLite + GPU
▲
MCP Agents ──MCP/HTTP──▶ MCP Server (Docker) ──┘
```
- **Engine**: Keeps the embedding model warm in memory. Handles search, ingestion, and document management via REST API. Runs in Docker with NVIDIA GPU, AMD GPU (ROCm), or CPU-only support.
- **Engine**: Keeps the embedding model warm in memory. Handles search, ingestion, document management, and note mutation via REST API. Runs in Docker with NVIDIA GPU, AMD GPU (ROCm), or CPU-only support.
- **Client**: Single static Go binary. No Python, no ML dependencies, instant startup. Talks to the engine over HTTP.
- **MCP Server**: Exposes kb operations as native MCP tools over Streamable HTTP. Runs as a separate Docker container alongside the engine. Supports collections for scoping agent memory vs user documents.
- **Storage**: Single SQLite database with FTS5 (keyword search) and sqlite-vec (vector search). Portable via bind mount — just copy the data directory between hosts.
## Quick start
@@ -84,7 +87,7 @@ Check [releases](https://gitea.dcglab.co.uk/steve/kb/releases) for the latest cl
```bash
# Set the version tag
TAG=client-v2.1.0
TAG=client-v3.0.0
# Linux (amd64)
curl -L -o kb https://gitea.dcglab.co.uk/steve/kb/releases/download/${TAG}/kb-linux-amd64
@@ -135,6 +138,9 @@ kb jobs
kb search "how to install git"
kb search "deploy process" --tags ops --type pdf
# Update a note in place
kb updatenote 42 "revised note content"
# Manage
kb list
kb info 1
@@ -182,6 +188,64 @@ KB_DATA_PATH=~/kb-data docker compose -f compose.nvidia.yaml up -d
Data is device-agnostic — you can ingest on NVIDIA and serve from AMD or CPU (or any combination) with the same data directory.
## MCP server (agent integration)
The MCP server exposes kb operations as native MCP tools, so agents can search, add notes, upload files, and manage documents without shelling out to the CLI.
### Start the MCP server
The compose files include a `kb-mcp` service alongside the engine. Set `KB_MCP_API_KEY` to require Bearer token auth from connecting agents:
```bash
KB_API_KEY=your-engine-key KB_MCP_API_KEY=your-agent-key \
docker compose -f engine/compose.nvidia.yaml up -d
```
Or run the MCP server standalone:
```bash
docker run -d --name kb-mcp \
-p 3000:3000 \
-e KB_ENGINE_URL=http://your-engine-host:8000 \
-e KB_API_KEY=your-engine-key \
-e KB_MCP_API_KEY=your-agent-key \
--restart unless-stopped \
docker.dcglab.co.uk/dcg/kb/mcp:latest
```
### MCP tools
| Tool | Description |
|---|---|
| `kb_search` | Hybrid search with optional collection/tag/type filters |
| `kb_addnote` | Add a text note (queued for async ingestion) |
| `kb_update_note` | Update an existing note in place |
| `kb_get` | Get document details by ID or source path |
| `kb_status` | Engine health and statistics |
| `kb_jobs` | Ingestion queue status |
| `kb_upload_start` | Start a chunked file upload |
| `kb_upload_chunk` | Upload a base64-encoded file chunk |
| `kb_upload_finish` | Finish upload and submit for ingestion |
### Collections
The MCP server supports **collections** — scoped document namespaces implemented via tag conventions. Use these to separate agent memory from user documents:
- `documents` (default) — user-facing documents
- `memory` — agent memory and preferences
- `workspace` — working context
Tools accept a `collection` parameter. The MCP server translates this to `collection:<name>` tags on the engine, and strips them from responses so agents see a clean `"collection": "memory"` field.
### MCP server configuration
| Variable | Default | Description |
|---|---|---|
| `KB_ENGINE_URL` | `http://localhost:8000` | Engine API URL |
| `KB_API_KEY` | (none) | Engine API key |
| `KB_MCP_API_KEY` | (none) | Bearer token required from agents (disabled if unset) |
| `KB_MCP_PORT` | `3000` | Port to listen on |
## Claude Code skill
This tool is designed to be wrapped as a Claude Code skill. See `SKILL.md` for the skill definition.