Your own AI client & MCP

Connect your own AI client

StepBerry speaks MCP, so an AI client you already use can read and write your procedures directly. Mint a token under Settings → Access tokens and point the client at https://stepberry.app/mcp. The token acts as you: it can do exactly what your role can do, and it stops working the moment you revoke it.

Connect your own AI

Locally, the assistant speaks to any OpenAI-compatible endpoint. Point it at Ollama, LM Studio, or anything else that answers on the same protocol:

STEPBERRY_AI_URL=http://localhost:11434   # default: Ollama
STEPBERRY_AI_MODEL=llama3.2

The cloud version includes a hosted model; no configuration needed there.

MCP: let your tools talk to your manual

StepBerry is an MCP server. A local AI client (Claude Desktop, an editor agent, anything MCP-aware) can search procedures, read sections, and manage canned answers through it. Locally it runs over stdio:

{
  "mcpServers": {
    "stepberry": { "command": "node", "args": ["src/mcp.ts"] }
  }
}

MCP over HTTP

The cloud workspace exposes the same tools at POST /mcp, guarded by an access token. Create one under Settings → Access tokens and send it as a bearer:

Authorization: Bearer sbk_…