A local Sumerian dictionary, literary corpus reader, and artifact-catalogue lookup β exposed to language models as MCP servers so AI agents can read 3,000-year-old clay tablets alongside you.
Local mirror of the electronic Pennsylvania Sumerian Dictionary (ePSD2), browsable by letter, searchable, with cuneiform glyphs rendered inline.
Five per-domain Model Context Protocol servers exposing the dictionary, the Oxford literary corpus, the CDLI artifact catalogue, and the Oracc sign list to AI agents.
Source code, build scripts, agent prompts, full setup guide.
Open source under MIT (code) with data layers separately
licensed β see LICENSE-DATA.md.
None of these datasets is unconditionally public-domain. All three have meaningful reuse conditions surfaced in every tool response and documented in LICENSE-DATA.md.
| Source | License | Notes |
|---|---|---|
| Oracc / ePSD2 / OGSL | CC BY-SA 3.0 | Attribution required; ShareAlike propagates to substantial reuses |
| ETCSL (Oxford) | Academic copyright | NOT under any Creative Commons license; citation is non-optional |
| CDLI | Mixed | Catalogue text reusable-with-citation; imagery non-commercial only. We host no imagery β all links point to cdli.earth |