How to Connect Oracle Database to Claude / Cursor via MCP (Oracle MCP Server Setup)

See everything Query Streams can do beyond this guide Get Started Free

Supports

+more

Live Data

Replace exports with on-demand SQL

Excel Sheets

BI & AI Analytics

Ask Nova, get SQL + charts

Meet Nova

Database REST API

One key per partner. No credentials shared.

Build an API

+more

Automation

Scheduled sync to 6+ platforms

Explore

+more

API to SQL

Query APIs with SQL, no code

Explore

+more

AI Database MCP

Claude, Cursor, ChatGPT & Grok talk to your data

Connect AI

Query Streams is a secure, real-time data integration platform that brings every database and SaaS API in your account into Claude, Cursor, ChatGPT, and Grok — through a single MCP key with no firewall changes. This guide walks through wiring up the Oracle MCP connector specifically, so your AI tool can answer plain-English questions about employees, departments, orders, financials, and any other Oracle Database data — joins, aggregations, PL/SQL dialect-specific syntax, schema exploration, ad-hoc reporting — without you copy-pasting CSV exports out of SQL Developer, Toad, or SQL*Plus. Whether you’re running Oracle 19c on-prem, Oracle Autonomous Database in OCI, Oracle XE on a developer workstation, or a RAC cluster on Exadata, the Oracle MCP server connects them all to your AI client through one key. Learn more at QueryStreams.com and sign up for free to start asking your AI tool real Oracle questions.

What Query Streams MCP gives you for Oracle Database

Other “Oracle MCP” servers on the open-source landscape connect the AI tool directly to an Oracle TNS connection string. That works, but it pushes a database password (and often a wallet) into your AI client’s config, scopes the AI tool to only that one Oracle endpoint, and gives you no audit trail of what the AI actually asked. The Query Streams MCP server for Oracle solves a wider problem: one key, every connector, full audit trail, and the AI tool never holds your Oracle credentials.

How it works without opening firewall ports

The Network Agent installs once on any host that can reach your Oracle Database over Oracle Net Services (TNS) and dials a single outbound TLS link to the cloud — nothing inbound is ever exposed, and the AI tool never sees your Oracle TNS connection string or wallet. how the outbound-only connection works →

The MCP key you give Cursor or Claude is scoped (read / analyze / execute), revocable at any time, and rate-limited per-key. The AI tool calls these MCP tools to do its work:

Why Schema Intelligence makes Query Streams MCP different

Most “MCP for Oracle” servers in the open-source landscape hand your AI tool the same ALL_TAB_COLUMNS view Oracle hands a stranger. Column names. Data types. Maybe a primary key. The LLM is left to guess what STATUS_CD = 'A' means, what EMP_NM_TXT actually stores, or which of two JOB_ID columns is the right one to join on (and whether the 30-character pre-12c column-name truncations changed the meaning). That’s why the first SQL most LLMs write against a bare Oracle schema is wrong — not because the LLM is bad, but because it doesn’t have the data it needs to be right, and Oracle’s data dictionary is dense.

Query Streams MCP returns that same schema enriched with what we call Schema Intelligence (SI) — AI-curated metadata that’s generated by running profiling queries against your actual Oracle data before the AI client ever asks. When SI is enabled on a connector and database, every schema tool the AI calls (qs_get_connector_schema, qs_get_table_schema, qs_profile_table, qs_get_relationships) returns the bare schema plus six layers of curated knowledge. The LLM stops guessing.

To make this concrete, here is what the AI client gets back from a single qs_get_table_schema call against a typical Oracle HR-style schema (employees, departments, jobs, locations, job_history) — first without Schema Intelligence, then with it.

The six layers Schema Intelligence adds

Each layer addresses a class of question the LLM would otherwise guess at. The opt-in SI profiling pass runs read-only against your Oracle data without changing your schema. what Schema Intelligence adds and how it stays current →

Same prompt, different SQL

The proof is in the SQL the AI tool actually writes. Same Cursor session, same Claude model, same prompt — “Show me the top 5 highest-paid employees who joined in the last year, including their total compensation and department.” Without Schema Intelligence the LLM guesses with PostgreSQL-flavored syntax that Oracle rejects. With it, the LLM knows the dialect.

MCP not for you? Try Nova AI instead.

Skip the JSON config entirely: Nova AI is built into the Query Streams web portal and asks the same plain-English questions against your Oracle connector — same agent, same read-only enforcement, same Schema Intelligence, no MCP plumbing.

Meet Nova AI

Prerequisites

Before you start, make sure you have:

1. A free Query Streams account at my.querystreams.com.
2. The Query Streams Network Agent installed on a machine that can reach your Oracle Database — see Download the Query Streams Agent.
3. An Oracle connector configured against the agent — see the existing connector setup guides for the TNS connection string. The agent holds the Oracle user password (or wallet, Kerberos, or directory-service credentials); the AI tool never touches them.
4. Any MCP-capable AI client. We’ll show Cursor, Claude Desktop, ChatGPT, and Grok in this guide; if you use Windsurf, Zed, Continue, Cline, VS Code Copilot, Codex, or Goose, the config block is essentially the same.
5. Five minutes.

Step 1: Generate an MCP key in Query Streams

Sign in to Query Streams and open the MCP page (or sign in first at my.querystreams.com and click MCP in the left navigation). Click Generate key, give the key a recognizable name (something like cursor-laptop or claude-desktop), and pick the scopes you want this key to have:

• read — the AI can browse connectors and read schema. Required for everything else.
• analyze — the AI can profile tables and discover relationships (sample values, distributions, semantic types). Optional but strongly recommended for Oracle work, where understanding the shape of your data matters when the LLM is generating joins across legacy schemas.
• execute — the AI can actually run SQL. Without this, the AI is read-only against schema metadata only.

For a typical “let Claude analyse my Oracle data” workflow, all three scopes are appropriate. For a key you’re handing to a teammate or a less-trusted client, drop execute and let them browse only. You can revoke any key at any time from the same page; the AI client will see MCP_KEY_REVOKED on its next call and stop working immediately. There’s no propagation delay.

Copy the key now — Query Streams shows it once, then stores only a hash. If you lose it, generate a new one. The key looks like qsmcp_ followed by 48 random characters and is what your AI client sends in the X-MCP-Key request header.

Step 2: Add Query Streams MCP to your AI client

The configuration is the same shape across every MCP-capable client — an MCP server entry pointing at https://mcp.querystreams.com with your key in the X-MCP-Key header. Pick your client below.

Cursor ~/.cursor/mcp.json

// Edit ~/.cursor/mcp.json
{
  "mcpServers": {
    "querystreams": {
      "url": "https://mcp.querystreams.com",
      "headers": {
        "X-MCP-Key": "qsmcp_PASTE_KEY_HERE"
      }
    }
  }
}

Claude Desktop claude_desktop_config.json

// Settings → Developer → Edit Config
{
  "mcpServers": {
    "querystreams": {
      "url": "https://mcp.querystreams.com",
      "headers": {
        "X-MCP-Key": "qsmcp_PASTE_KEY_HERE"
      }
    }
  }
}

ChatGPT Apps & Connectors

// Settings → Apps & Connectors → Add MCP
Server URL  https://mcp.querystreams.com
Auth header X-MCP-Key
Header value qsmcp_PASTE_KEY_HERE

// Requires a paid ChatGPT plan
// (Plus / Pro / Team / Enterprise).

Grok Remote MCP Tools

// Grok → Settings → Tools
{
  "mcp_servers": [{
    "name": "querystreams",
    "url": "https://mcp.querystreams.com",
    "auth_header": "X-MCP-Key",
    "auth_value": "qsmcp_..."
  }]
}

Restart your AI client. On its next start it will discover the eight Query Streams MCP tools listed above and surface them in its tool palette. In Cursor and Claude Desktop you can verify by typing “list connectors” — the AI should call qs_list_connectors and return your Oracle connector along with anything else you have configured.

Step 3: Ask the AI an Oracle question

You don’t write SQL — the AI does. You ask a question, the AI picks the right MCP tool, the agent runs the query against your Oracle Database, and the answer comes back as text plus tables. Three example prompts to try first:

The first time the AI calls a tool, your client may pop up a confirmation prompt asking you to approve the tool call — that’s MCP’s standard consent flow, not anything Query Streams adds. Approve once and the AI proceeds with the rest of the conversation freely. You can revisit the consent at any time in your client’s settings.

Frequently asked questions

Get started

Related guides: Download the Query Streams Agent | Database Connector Setup | All MCP Server guides | Nova AI text-to-SQL

Category: MCP Server

Tags: mcp, claude, cursor, oracle, oracle-database, database, enterprise, autonomous-database

Meta Description: Connect Oracle Database to Claude or Cursor via Query Streams MCP. Autonomous, RAC, Exadata, 19c. Outbound-only, read-only, 5-min setup.