Can I create an Agent & still use MCP SQLcl Server? Yes!

This is just a quick and dirty post to answer a question I’ve been receiving lately. “Hey, instead of using Copilot, or Claude, or Windsurf, or Klein, or…can we create our own agent?”

YES, yes, you can.

Proof that any fool (me, not you dear reader!) can code an AI Agent, and connect it to their Oracle AI Database via our MCP Server, Oracle SQLcl –

MCP SQLcl Server Logs – conveniently stored in your database

With not too much python code, I can get a chat prompt that allows me to ask natural language questions to interact with my Oracle database.

Party
thatjeffsmith$ /Users/thatjeffsmith/langchain/.venv/bin/python main.py

============================================================
NL2SQL Chat Agent - Oracle Database Edition
Powered by LangChain + Claude + MCP
============================================================

Initializing agent...
Agent ready! Type 'exit' or 'quit' to end the session.
                                  
You: Connect to Project Raptor 🦖 database and find the highest paid employee by salary

Agent: ---------- MCP SERVER STARTUP ----------
MCP Server started successfully on Mon Dec 01 14:55:19 EST 2025
Press Ctrl+C to stop the server
----------------------------------------
Dec 01, 2025 2:55:20 PM 
## Summary

I successfully connected to the **Project Raptor 🦖** database and found the highest paid employee:

**Highest Paid Employee:**
- **Name:** Steven King
- **Employee ID:** 100
- **Email:** SKING
- **Job Title:** AD_PRES (President)
- **Salary:** $24,000
- **Department:** Executive (Department ID: 90)

Steven King is the President of the company and works in the Executive department, earning the highest salary of $24,000 among all employees in the database.

You: kthxbye
thatjeffsmith$ /Users/thatjeffsmith/langchain/.venv/bin/python main.py

============================================================
NL2SQL Chat Agent - Oracle Database Edition
Powered by LangChain + Claude + MCP
============================================================

Initializing agent...
Agent ready! Type 'exit' or 'quit' to end the session.
                                  
You: Connect to Project Raptor 🦖 database and find the highest paid employee by salary

Agent: ---------- MCP SERVER STARTUP ----------
MCP Server started successfully on Mon Dec 01 14:55:19 EST 2025
Press Ctrl+C to stop the server
----------------------------------------
Dec 01, 2025 2:55:20 PM 
## Summary

I successfully connected to the **Project Raptor 🦖** database and found the highest paid employee:

**Highest Paid Employee:**
- **Name:** Steven King
- **Employee ID:** 100
- **Email:** SKING
- **Job Title:** AD_PRES (President)
- **Salary:** $24,000
- **Department:** Executive (Department ID: 90)

Steven King is the President of the company and works in the Executive department, earning the highest salary of $24,000 among all employees in the database.

You: kthxbye

Prefer Java? Then you can follow Anders’ example complete with code!

Anders is a developer advocate at Oracle. He is a ‘real developer’ – you can believe that his code is much more enterprise ready than mine!

Click on the image to read the blog post. Click here to go directly to the source code.

Neither Anders nor I did a local LLM. In my python project, I use the Claude Console API key to access and use their Claude Sonnet 4 model. Anders uses OpenAI’s gpt-40-mini model.

If you are building your own AI Agent, you will probably WANT to run your LLM locally – this will ensure your data doesn’t leave your environment. Remember, MCP doesn’t care what model or agency you use…

I won’t show my code yet

I put it together in under an hour, and it wasn’t brilliant.

However, here are my system commands –

Party
self.system_prompt = """You are an expert SQL assistant with access to an Oracle database.
Your role is to:
1. Understand natural language questions about data
2. Generate accurate SQL queries to answer those questions
3. Execute the SQL using the available tools
4. Summarize the results in a clear, understandable way

When a user asks a question:
- First, use get_schema_info if you need to understand the database structure
- Then generate the appropriate SQL query
- Execute it using execute_sql
- Finally, provide a clear summary of the results

Always ensure your SQL queries are safe and follow Oracle SQL syntax.
"""
self.system_prompt = """You are an expert SQL assistant with access to an Oracle database.
Your role is to:
1. Understand natural language questions about data
2. Generate accurate SQL queries to answer those questions
3. Execute the SQL using the available tools
4. Summarize the results in a clear, understandable way

When a user asks a question:
- First, use get_schema_info if you need to understand the database structure
- Then generate the appropriate SQL query
- Execute it using execute_sql
- Finally, provide a clear summary of the results

Always ensure your SQL queries are safe and follow Oracle SQL syntax.
"""

My python get_schema_info method uses hard-coded SQL statements to get information about the schema, NOT using the new schema information MCP tool. That will be my next step to get this code, shareable.

This is my mcp server configuration –

JSON
{
  "command": "/opt/sqlcl/25.3/sqlcl/bin/sql",
  "args": ["-mcp"],
  "type": "stdio",
  "env": {}
}
{
  "command": "/opt/sqlcl/25.3/sqlcl/bin/sql",
  "args": ["-mcp"],
  "type": "stdio",
  "env": {}
}

So yes, it’s local, it will work fine with my local python agent running in my terminal.

Testing my MCP Server

Here’s a python stub to see if I can see/access the MCP Server –

python
from src.agent import NL2SQLAgent
import json

# Load config
with open('config/mcp_config.json') as f:
    config = json.load(f)

# Test the agent
agent = NL2SQLAgent(config)
print('Agent initialized!')
print()

# Test a simple query
response = agent.chat('List all available database connections')
print('Response:', response)

agent.close()
from src.agent import NL2SQLAgent
import json

# Load config
with open('config/mcp_config.json') as f:
    config = json.load(f)

# Test the agent
agent = NL2SQLAgent(config)
print('Agent initialized!')
print()

# Test a simple query
response = agent.chat('List all available database connections')
print('Response:', response)

agent.close()

And running my test program: voila!

Party
Agent initialized!

---------- MCP SERVER STARTUP ----------
MCP Server started successfully on Tue Dec 02 15:33:08 EST 2025
Press Ctrl+C to stop the server
----------------------------------------
Response: Here are all the available Oracle database connections:

1. **Project Raptor 🦖**
2. **Free26ai**
3. **🅾️ Autonomous Reporting**
4. **system**
5. **Project Payroll 💲**
6. **HR123**
7. **ADMIN**
8. **demo**
9. **windy**

You can connect to any of these databases by specifying the connection name. Would you like me to connect to one of these databases so you can start querying data?

Server shutting down...

Macmini:langchain thatjeffsmith$ 
Agent initialized!

---------- MCP SERVER STARTUP ----------
MCP Server started successfully on Tue Dec 02 15:33:08 EST 2025
Press Ctrl+C to stop the server
----------------------------------------
Response: Here are all the available Oracle database connections:

1. **Project Raptor 🦖**
2. **Free26ai**
3. **🅾️ Autonomous Reporting**
4. **system**
5. **Project Payroll 💲**
6. **HR123**
7. **ADMIN**
8. **demo**
9. **windy**

You can connect to any of these databases by specifying the connection name. Would you like me to connect to one of these databases so you can start querying data?

Server shutting down...

Macmini:langchain thatjeffsmith$ 

Looking for more content on how to complete tasks with our MCP Server?

See Chris’ post on blogs.oracle.com –

Or join our live guided LiveLab!

Berita Terkini

Berita Terbaru

Daftar Terbaru

News

Berita Terbaru

Flash News

RuangJP

Pemilu

Berita Terkini

Prediksi Bola

Togel Deposit Pulsa

Technology

Otomotif

Berita Terbaru

Daftar Judi Slot Online Terpercaya

Slot yang lagi gacor

Teknologi

Berita terkini

Berita Pemilu

Berita Teknologi

Hiburan

master Slote

Berita Terkini

Pendidikan

Resep

Jasa Backlink

One Piece Terbaru