Poster presented at the CCLS 2026, Potsdam
\nThe \"DraCor Open Knowledge Graph,\" developed in the DraCorOS project (OSCARS Cascading Grant), links dramatic texts, their metadata, computational tools, publications, and training materials as semantically enriched Linked Open Data, modelled with CIDOC-CRM, LRMoo, CRMdig, and a slim DraCor extension. Yet querying it requires SPARQL—a barrier that leaves such expert systems under-used by the humanities scholars who would benefit most. This poster presents an approach to democratizing access by implementing a Model Context Protocol (MCP) server that lets Large Language Models autonomously query the graph: users ask in plain language, the model writes and runs the SPARQL, and answers in prose. The central challenge is \"docstring engineering\"—designing tool documentation that teaches the model the data model, query patterns, namespaces, named graphs, and dataset quirks.
", "languages": [ { "id": "eng", "title": { "en": "English" } } ], "publication_date": "2026-05-28", "publisher": "Zenodo", "resource_type": { "id": "poster", "title": { "de": "Poster", "en": "Poster" } }, "rights": [ { "description": { "en": "The Creative Commons Attribution license allows re-distribution and re-use of a licensed work on the condition that the creator is appropriately credited." }, "icon": "cc-by-icon", "id": "cc-by-4.0", "props": { "scheme": "spdx", "url": "https://creativecommons.org/licenses/by/4.0/legalcode" }, "title": { "en": "Creative Commons Attribution 4.0 International" } } ], "title": "Agentic Access to Linked Open Data: An MCP Server for Chat Interaction with the DraCor Open Knowledge Graph" }, "parent": { "access": { "owned_by": { "user": "23139" }, "settings": { "accept_conditions_text": null, "allow_guest_requests": false, "allow_user_requests": false, "secret_link_expiration": 0 } }, "communities": { "default": "7e213314-709e-44cb-bf6e-1228e229e07c", "entries": [ { "access": { "member_policy": "open", "members_visibility": "public", "record_submission_policy": "open", "review_policy": "open", "visibility": "public" }, "children": { "allow": false }, "created": "2023-10-16T09:41:08.130661+00:00", "custom_fields": { "subjects": [ { "id": "euroscivoc:49932688" } ] }, "deletion_status": { "is_deleted": false, "status": "P" }, "id": "7e213314-709e-44cb-bf6e-1228e229e07c", "links": {}, "metadata": { "curation_policy": "In this Zenodo collection we gather research empowered by DraCor (Drama Corpora Project). The studies (papers, presentation slides, data sets) in this collection illustrate the broad applicability of DraCor's resources – TEI-XML encoded corpora, the DraCor API and various tools of the DraCor ecosystem – in researching dramatic texts within the field of Computational Literary Studies.
\nWe welcome submissions of research that has utilized DraCor. For a comprehensive list please visit the Research page on dracor.org.
\n", "page": "", "title": "DraCor", "type": { "id": "project" }, "website": "https://dracor.org" }, "revision_id": 10, "slug": "dracor", "updated": "2025-03-12T15:14:05.434354+00:00" } ], "ids": [ "7e213314-709e-44cb-bf6e-1228e229e07c" ] }, "id": "20422859", "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.20422859", "provider": "datacite" } } }, "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.20422860", "provider": "datacite" }, "oai": { "identifier": "oai:zenodo.org:20422860", "provider": "oai" } }, "revision_id": 4, "stats": { "all_versions": { "data_volume": 56348224.0, "downloads": 16, "unique_downloads": 15, "unique_views": 26, "views": 27 }, "this_version": { "data_volume": 56348224.0, "downloads": 16, "unique_downloads": 15, "unique_views": 26, "views": 27 } }, "status": "published", "swh": {}, "updated": "2026-05-28T05:34:27.868363+00:00", "versions": { "index": 1, "is_latest": true } }