What it does
Tugra is a memory format for AI agents in which each stored claim is recorded together with its source, its age and its boundary. The publisher describes this provenance tracking as the core idea of the project.
It is relevant to developers who want an agent's remembered facts to show where they came from and how old they are, rather than being stored as bare statements. The publisher's description does not specify which agent frameworks or workflows it is designed for.
Tugra is distributed as an MCP server, and the source repository is hosted on GitHub. The publisher's facts do not describe installation steps or setup requirements.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
Tugra
Provenance-aware memory format for AI agents: every claim carries its source, age and boundary.
v0.1.4As shown on registry.modelcontextprotocol.io when we last read it