Oracle Vector Store
This MCP server provides semantic search capabilities over Oracle Vector Store databases, enabling natural language queries against document collections stored in Oracle Database with vector embeddings. Built by Luigi Saetta, it integrates Oracle's vector database technology with OCI GenAI services for embeddings and includes optional JWT-based authentication through Oracle Identity Cloud Service for enterprise security. The implementation offers two variants: a standard semantic search tool that returns full document content, and a Deep Research-compatible version that follows OpenAI's specification with separate search and fetch operations for integration with ChatGPT's research workflows. It's particularly valuable for enterprise knowledge bases, document retrieval systems, and research applications where users need to query large document collections using conversational language while maintaining enterprise-grade security and leveraging Oracle's database infrastructure.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/luigisaetta/mcp-oci-integration
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Oracle Vector Store from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.