Use Oracle Database with your AI.
Connect your account once and let the AI you already use work with it, without building another integration. Run vector similarity searches on Oracle 23ai. execute VECTOR_DISTANCE queries, inspect schemas, list vector indexes, and query tables from any AI agent.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Complete set · 7 capabilities
The complete Oracle Database capability set.
These are the exact actions your AI can choose when you ask it to work with Oracle Database.
01-04
4 capabilities in this set.
Part of 7 available through Oracle Database.
- 01
Execute SQL query
WARNING: Output payload size is inherently limited, restrict rows fetched (FETCH FIRST 100 ROWS ONLY) to ensure stability. Execute arbitrary SQL query against the Oracle runtime via ORDS
- 02
Get database version
Get exact Oracle DB Runtime version banner
- 03
Table stats
Get table cardinality and optimizer statistics
- 04
Describe table
Describe table columns and explicit data types including VECTORs
05-07
3 capabilities in this set.
Part of 7 available through Oracle Database.
- 05
List tables
List accessible tables in the current Oracle schema
- 06
List vector indexes
List specialized AI Vector search indexes (HNSW, IVF) instantiated
- 07
Vector search
1, -0.4, 0.5] against a strict VECTOR` column natively inside Oracle DB, sorting and fetching the nearest neighbors. Execute Vector similarity search via Oracle 23ai native VECTOR_DISTANCE
Observed, not estimated
832ms average. Fast in production.
Oracle Database is checked daily against the live service.
- Fastest day
- 693ms
- Slowest day
- 1032ms
- 14-day trend
- Slowing+15%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 7 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Oracle Database, so you can see the experience inside your AI.
It does not authenticate your account with Oracle Database. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
Oracle Database Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_Bs3fBgLmPqQPV1iPDfqOKsvG2g10fcqpkDZdhwp8/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Oracle Database capabilities are ready to use.
{
"mcpServers": {
"oracle-vector-db-mcp": {
"url": "https://edge.vinkius.com/vk_preview_Bs3fBgLmPqQPV1iPDfqOKsvG2g10fcqpkDZdhwp8/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
FAQ
Questions Oracle Database owners ask.
- 01
Does it work with Oracle Autonomous Database?
Yes. Oracle Autonomous Database on OCI has ORDS enabled by default. Use the ORDS URL from your ADB instance (e.g., https://xxxxx.adb.us-ashburn-1.oraclecloudapps.com/ords), your schema name (typically ADMIN), and the admin credentials. The VECTOR type is available on all 23ai-compatible instances.
- 02
Can I run arbitrary SQL. not just vector searches?
Yes. The execute_sql_query capability accepts any valid Oracle SQL statement and returns results through ORDS. Add FETCH FIRST N ROWS ONLY to keep payloads manageable. This makes the agent useful for relational queries too, not just vector operations.
- 03
Which distance metrics are available for vector search?
Oracle 23ai supports COSINE and EUCLIDEAN (L2) distance metrics natively via VECTOR_DISTANCE. Specify the metric when running a search. cosine is recommended for most text embedding use cases, while L2 works better for image or audio embeddings.
Explore
More in Industry Titans
Vertex AI Vector Search AI Connector
Bring Google's massive vector matching power to your AI agent. Search billions of semantic embeddings and admi
Viewpgvector (Vector Database) AI Connector
Run vector similarity searches, manage embedding tables, and build AI-powered retrieval pipelines — all direct
ViewSupabase Vector AI Connector
Connect your AI to Supabase Vector. Execute pgvector semantic searches, manage embeddings, and run relational
ViewLanceDB (Serverless Vector DB) AI Connector
Manage vectorized data via LanceDB — perform similarity searches, create tables, and manage multi-modal embedd
View
Suggestions
Vald AI Connector
Power your agent with Vald — query, insert, and manage dense vectors on a highly scalable, distributed nearest
ViewMongoDB Atlas Vector Search AI Connector
Manage vector storage via MongoDB Atlas — perform similarity searches, query MQL documents, and audit collecti
ViewMilvus (Open-Source Vector Database) AI Connector
Manage vector storage via Milvus — perform ANN searches, query scalar entities, and audit collections.
ViewR2R AI Connector
Equip your AI with direct access to your R2R engine — execute vector searches, run precise RAG queries, and ma
View
