Skip to content

Commit 6b015a0

Browse files
authored
Merge branch 'main' into compute-review2025
2 parents 2325039 + a01cbfd commit 6b015a0

File tree

3 files changed

+28
-2
lines changed
  • ai/gen-ai-agents
  • app-dev/app-integration-and-automation/oracle-integration-cloud/10-oic-instance-migration-key-considerations

3 files changed

+28
-2
lines changed

ai/gen-ai-agents/mcp-oci-integration/README.md

Lines changed: 23 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -8,6 +8,10 @@ This repository contains code and examples to help in the following tasks:
88
* **Integrate** MCP Servers with OCI **APM** for **Observability**
99
* **how-to** create a **docker** image for your MCP server
1010

11+
**Author**: L. Saetta
12+
13+
**Reviewed**: 15.10.2025
14+
1115
![MCP console](./images/mcp_cli.png)
1216

1317
## What is MCP?
@@ -51,7 +55,7 @@ The code is available [here](./mcp_semantic_search_with_iam.py).
5155

5256
Access to Oracle 23AI Vector Search is through the **new** [langchain-oci integration library](https://github.com/oracle/langchain-oracle)
5357

54-
## Adding security
58+
## Adding Security
5559
If you want to put your **MCP** server in production, you need to add security, at several levels.
5660

5761
Just to mention few important points:
@@ -84,4 +88,22 @@ An example is [here](./mcp_selectai.py)
8488

8589
For **Select AI** configuration, see [here](./configure_select_ai.md)
8690

91+
## OCI Consumption Analysis
92+
Another use case demonstrated in this set of demos is leveraging an AI Assistant powered by MCP servers to analyze the **OCI tenant consumption** in a natural and interactive way.
93+
94+
Using the [MCP Consumption Server](./mcp_consumption.py), you can explore various dimensions of consumption and ask questions such as:
95+
* List the top 10 services by total amount for a given period (start_date, end_date).
96+
* List the top 10 compartments by total consumption.
97+
* For a specific service (or list of services), show the consumption breakdown across the top 5 compartments.
98+
99+
The key advantage of this approach is that you don’t need to export or replicate data into a Data Warehouse (DWH) — all information is retrieved directly from the OCI Usage API in real time.
100+
101+
How to Use:
102+
* Configure your OCI credentials.
103+
* Start the MCP Consumption Server
104+
* Launch the AI Assistant
105+
* Point the Assistant to the MCP URL (or to your MCP Aggregator).
106+
107+
### Security (Optional)
108+
You can enhance security by placing the MCP server behind an OCI API Gateway and enabling JWT-based authentication using OCI IAM.
87109

ai/gen-ai-agents/travel-agent/README.md

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -4,6 +4,10 @@ The AI Agent enables a customer to get information about available destinations
44

55
The agent has been developed using **OCI Generative AI** and **LangGraph**.
66

7+
**Author**: L. Saetta
8+
9+
**Reviewed**: 15.10.2025
10+
711
## Configuration
812
You only need to create a file, named config_private.py, with the value for **COMPARTMENT_OCID**.
913
The compartment must be a compartment where you have setup the right policies to access OCI Generative AI.
Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -14,7 +14,7 @@ Refer to the official documentation: [Export and Import Design-Time Metadata](ht
1414
This ensures your core integration logic is replicated, but it’s only part of the migration picture.
1515

1616
---
17-
17+
10-oic-instance-migration-key-considerations
1818
## 2. User and Access Management
1919
- Users, roles, and access policies are not carried over automatically.
2020
- Recreate the necessary user and role assignments for the new instance.

0 commit comments

Comments
 (0)