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

Split MCP docs into MCP.md with AI tool setup examples

Browse Source 
Move MCP server documentation from README into dedicated MCP.md.
Add configuration examples for Claude Code, VS Code, Cursor,
Windsurf, and JetBrains IDEs.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Steve Cliff
2026-04-02 22:03:41 +01:00
parent b3dce188e1
commit d078af9ad3
2 changed files with 178 additions and 56 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4 -56
View File
@@ -190,62 +190,10 @@ Data is device-agnostic — you can ingest on NVIDIA and serve from AMD or CPU (
## 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.
The MCP server exposes kb operations as native MCP tools over Streamable HTTP, so agents can search, add notes, upload files, and manage documents without shelling out to the CLI. Includes setup guides for Claude Code, VS Code, Cursor, Windsurf, and JetBrains IDEs.
### Start the MCP server
See **[MCP.md](MCP.md)** for full details — server setup, available tools, collections, configuration, and client examples.
The compose files include a `kb-mcp` service alongside the engine. Set `KB_MCP_API_KEY` to require Bearer token auth from connecting agents:
## Agent skill
```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.
If you are restricted from using MCP server, or you just prefer to utilise Agent SKILLS, please also see `SKILL.md` for the skill definition.