MCP For Claude Marketplace
Oracle Vector DB

Oracle Vector DB MCP Connector for Claude

A+

Run vector similarity searches on Oracle 23ai — execute VECTOR_DISTANCE queries, inspect schemas, list vector indexes, and query tables from any AI agent.

7 tools Official Updated Jun 28, 2026 Official Vinkius Partner
More Details Connect to Claude

Bring your Oracle Database 23ai vector capabilities directly into your AI agent workflow. Run VECTOR_DISTANCE similarity searches, inspect table schemas, execute SQL queries, and manage vector indexes — all through natural conversation.

What you can do

  • Vector Similarity Search — Execute native Oracle 23ai VECTOR_DISTANCE queries with cosine or Euclidean metrics against any table with VECTOR columns
  • Schema Inspection — List all tables in your schema and describe column types, spotting VECTOR-enabled columns for embedding storage
  • SQL Execution — Run arbitrary SQL queries against Oracle via ORDS for ad-hoc analysis and data retrieval
  • Vector Index Management — List all HNSW and IVF vector indexes instantiated across your tables
  • Table Statistics — Get row counts and optimizer stats for capacity planning and query performance tuning
  • Version Check — Verify your Oracle runtime version to confirm 23ai vector feature compatibility

How it works

  1. Subscribe to this server
  2. Enter your Oracle ORDS URL, Schema, Username, and Password
  3. Start querying your vector store from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • Enterprise data teams — run vector searches against production Oracle databases without context-switching to SQL Developer
  • ML engineers — test embedding queries on Oracle 23ai's native vector engine during RAG pipeline development
  • DBAs — inspect vector indexes, table stats, and schema configurations through conversation
vector-databasesqlragmachine-learningdatabase-administrationsimilarity-search

7 tools expose this connector's capabilities to your AI agent.

list_tables

List accessible tables in the current Oracle schema

describe_table

Describe table columns and explicit data types including VECTORs

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

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

list_vector_indexes

List specialized AI Vector search indexes (HNSW, IVF) instantiated

table_stats

Get table cardinality and optimizer statistics

get_database_version

Get exact Oracle DB Runtime version banner

See how to talk to your AI agent using Oracle Vector DB.

Show me all tables in my schema that have VECTOR columns.

Found 3 tables with VECTOR columns. 1) DOCUMENTS — columns: ID (NUMBER), CONTENT (CLOB), EMBEDDING (VECTOR(1536)), 82,400 rows. 2) PRODUCTS — columns: ID, NAME, FEATURES_VECTOR (VECTOR(768)), 5,200 rows. 3) FAQ_ENTRIES — columns: ID, QUESTION, ANSWER_EMBEDDING (VECTOR(384)), 1,100 rows. Want me to search one?

Find the 5 most similar documents to this embedding using cosine distance.

Top 5 results from DOCUMENTS table (cosine): 1) Doc #4521 — 'API Rate Limits Overview', distance: 0.034. 2) Doc #1892 — 'Authentication Flow Guide', distance: 0.089. 3) Doc #7301 — 'Error Handling Reference', distance: 0.112. 4) Doc #2244 — 'SDK Quickstart', distance: 0.145. 5) Doc #9010 — 'Webhook Setup', distance: 0.178.

What version of Oracle is running and does it support vectors?

Oracle Database 23ai (23.4.0.24.05) — Free tier. Vector features: fully supported. VECTOR data type: available. VECTOR_DISTANCE function: available. HNSW index support: yes. Your instance is ready for vector similarity search operations.

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.

Related Connectors

AL

Allnodes (Staking and Web3 Hosting API) MCP

20 tools Official

Manage staking, validators, and Web3 hosting infrastructure directly from any AI agent via Allnodes.

F View details →
VC

vCard Contacts Parser MCP

1 tools Official

Instantly convert massive iPhone and Android `.vcf` contact exports into structured JSON. Turn your AI into a hyper-intelligent local address book.

F View details →
OS

Odoo Sales MCP

8 tools Official

Create quotations, confirm sales orders, manage products and pricelists — Odoo Sales pipeline through natural conversation.

A+ View details →
WI

Winevybe MCP

10 tools Official

Automate sommelier intelligence via Winevybe — search global wine catalogs, check vineyard ratings, and manage virtual cellars directly from any AI agent.

A+ View details →