Your agent has tools. Does it have the right evidence? Connecting Jylus through MCP

Описание и применение

Разработчики могут подключать Jylus к агентам через MCP, запрашивая доказательства и состояние, чтобы проверить ответы.

Agents can call multiple tools but may still produce incorrect answers if evidence is not correctly linked or verified.

Agents can now retrieve and verify evidence through MCP, reducing the risk of incorrect answers.

1. Ingest records into Jylus workspace.
2. Configure client to connect to https://api.jylus.ai/api/mcp with a workspace API key (events:read).
3. Call "get_context_pack" with a question, namespace, date range, and token budget.
4. Inspect returned evidence pack and resolve state via "resolve_state" if needed.
5. Use "get_evidence" to view original source records referenced by proof IDs.
6. Verify that evidence supports the agent’s answer and check for disagreements or missing records.

Your agent successfully calls three tools.

I’m the founder of Jylus. We built an evidence and state layer that prepares source-backed context before a model reasons.

Model Context Protocol gives AI applications a standard way to discover and call tools exposed by a server.