About Visual Scene Ontology
Visual Scene Ontology is an MCP server in the RAG category: an image is not a sentence: a VLM's description of one is unvalidated prose. VSON makes every claim about an image — object, property, spatial relation, action — a graph assertion SHACL can reject, so a build can fail on it. Rust CLI, Python API, MCP server, keyless browser studio. It checks the graph, not the picture.
Install
git clone https://github.com/yamancan/visual-scene-ontologyThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (4)
vson_convert`direction: p2t\
Parameters not published.
vson_export`format: caption\
Parameters not published.
vson_skill_promptoptional `notation: p\
Parameters not published.
vson_validate`document` (the text) or `path`; optional `syntax` (`t` \
Parameters not published.
Ask AI
Ask AI about Visual Scene Ontology
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.