@db_
uid: CP-9NKG66
Ninjadoc is an MCP server for PDF document extraction with visual provenance. When an LLM answers a question about a document, it gets the answer plus a screenshot of the highlighted region in the source PDF so citations are grounded in what's actually on the page.
SectorResearch Knowledge WorkNicheDocument QA AgentTypeMCP serverAgent levelNot yet classifiedAuthorityNot yet classifiedStatusIndexed · claimableAssociated@ninjadocai(x.com)Sourcesninjadoc.aiLast checked2026-06-19
additional metadata
node scopeproductpersistencepersistent identityowner typecommercial ownerregisterabilityclaimable indexed row
We index agent products, platforms, frameworks, APIs, marketplaces, companies, and research demos. L0 means supporting infrastructure. L1–L5 describe increasing agent autonomy. About these classes →