OSIRIS-MCP: Towards secure conversational access to research information in OSIRIS
Abstract
Research information systems contain structured information about researchers, organisational units, projects, publications, and other research activities. However, answering ad hoc questions for reporting, management, or public communication often still requires manual searches, exports, and synthesis. We developed a prototype Model Context Protocol (MCP) connector for OSIRIS, an open-source research information system, during the DBCLS BioHackathon 2026. The connector gives language-model clients read-only access to a deliberately restricted set of typed search and retrieval tools. It combines a compact, evidence-centred data representation with instance-specific metadata discovery, bounded pagination, dedicated API-client permissions, safe error handling, and either OAuth or static API-key authentication. The work also introduced a general API-client registry in OSIRIS, allowing integrations to receive independently revocable credentials and explicitly assigned permissions. A containerised deployment was validated against a local OSIRIS instance containing synthetic data and tested interactively with MCP clients. The prototype demonstrates that conversational access to institutional research information can be implemented without exposing complete database records or making the language model responsible for access control. Evaluation with real institutional data and deployment guidance remain necessary before production use.
Related
- M3: Conversational LLMs simplify secure clinical data access, understanding, and analysis
- Social relationships promote access to food and information in wild jackdaws.
- Open access route and citation impact in orthopaedic research: A comparison of Gold/hybrid, Green, and Bronze open access within ten high-impact subscription-based journals
- Investigating strategies to enhance access to HIV services among children in Malawi: A multifaceted research approach, study protocol
- Research on multimodal dense small object detection algorithms guided by cross-modal information
BibTeX
@misc{koblitz2026osirismcp,
title = {{OSIRIS-MCP: Towards secure conversational access to research information in OSIRIS}},
author = {Julia Koblitz and Akira R Kinjo},
howpublished = {BioHackrXiv},
year = {2026},
month = sep,
doi = {10.37044/osf.io/36g4c_v3},
url = {https://osf.io/preprints/biohackrxiv/36g4c_v3/},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - OSIRIS-MCP: Towards secure conversational access to research information in OSIRIS
AU - Julia Koblitz
AU - Akira R Kinjo
PY - 2026
DA - 2026/09/18
PB - BioHackrXiv
DO - 10.37044/osf.io/36g4c_v3
UR - https://osf.io/preprints/biohackrxiv/36g4c_v3/
AB - Research information systems contain structured information about researchers, organisational units, projects, publications, and other research activities. However, answering ad hoc questions for reporting, management, or public communication often still requires manual searches, exports, and synthesis. We developed a prototype Model Context Protocol (MCP) connector for OSIRIS, an open-source research information system, during the DBCLS BioHackathon 2026. The connector gives language-model clients read-only access to a deliberately restricted set of typed search and retrieval tools. It combines a compact, evidence-centred data representation with instance-specific metadata discovery, bounded pagination, dedicated API-client permissions, safe error handling, and either OAuth or static API-key authentication. The work also introduced a general API-client registry in OSIRIS, allowing integrations to receive independently revocable credentials and explicitly assigned permissions. A containerised deployment was validated against a local OSIRIS instance containing synthetic data and tested interactively with MCP clients. The prototype demonstrates that conversational access to institutional research information can be implemented without exposing complete database records or making the language model responsible for access control. Evaluation with real institutional data and deployment guidance remain necessary before production use.
ER -