oci-mcp-server
About
oci-mcp-server is a Python MCP (Model Context Protocol) server for Oracle Cloud Infrastructure (OCI) API Gateway management. It provides tools to list and retrieve details of API Gateways, and supports both programmatic clients and LLM-powered agents (via stdio transport…
Explore
- List API Gateways in a given OCI compartment.
- Get details for a specific API Gateway.
- MCP stdio transport for easy integration with LLM agents and other clients.
- LlamaIndex/Ollama client for natural language interaction with OCI API Gateway resources.
---
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
oci-mcp-serverCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Edit src/config.py to set your OCI compartment and gateway OCIDs, region, and profile as needed:
PROFILE_NAME = 'DEFAULT'
REGION = 'ap-mumbai-1'
SERVICE_ENDPOINT = '<SERVICE ENDPOINT>'
COMPARTMENT_ID = '<COMPARTMENT_ID>'
GATEWAY_ID = '<GATEWAY_ID>' # For Programmatic Client
You must have valid OCI session files in ~/.oci/sessions/DEFAULT/.
You can do so by something like this oci session authenticate --tenancy-name <TENANCY_NAME> --profile-name DEFAULT --region $REGION
---
- Python 3.11 (required)
- uv (fast Python package/dependency manager)
- OCI account with API Gateway access
- OCI session authentication files (~/.oci/sessions/DEFAULT/token and oci_api_key.pem)
curl -Ls https://astral.sh/uv/install.sh | sh
Or, from PyPI:
bashuv venv --python 3.11
source .venv/bin/activate
bashuv pip install -r pyproject.toml
Or, if you want to use uv directly:
bashuv pip install -e .
---
Cursor is an AI-powered code editor that can natively interact with MCP servers.
To install Cursor:
- Download and install Cursor from the official website for your platform (macOS, Windows, Linux).
- Follow the installation instructions for your OS.
To connect Cursor to your custom MCP server, you need to update or create an mcp.json file in your project root. Use the provided template in src/mcp_template.json as a starting point.
Steps
1. Open Cursor Settings by navigating to Cursor > Settings... > Cursor Settings
2. Select MCP > + Add new global MCP server
You should also be able to edit mcp.json from vi ~/.cursor/mcp.json
Steps:
1. Copy the content of src/mcp_template.json to ~/.cursor/mcp.json (or to mcp.json from the editor):
2. Edit mcp.json and update the paths:
- Replace <path to Python> with the absolute path to your Python 3.11 executable if using a virtual environment).
- Replace <path to server.py> with the absolute path to your server.py script.
3. Save the file. Cursor will now be able to discover and connect to your MCP server.
---
From the project root: (I have found that its better to run the server in a separate terminal)
bashpython src/server.py
``
This will start the MCP server using stdio transport, exposing the following tools:
-
list_gateways_tool(compartment_id)
- get_gateway_tool(gateway_id)`
---
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"oci-mcp-server": {
"oci-mcp-server": {
"command": "uv",
"args": [
"self-update"
]
}
}
}
}
McpServers
{
"oci-mcp-server": {
"command": "uv",
"args": [
"self-update"
]
}
}
A Python MCP (Multi-Client Protocol) server for Oracle Cloud Infrastructure (OCI) API Gateway management, with both programmatic and LLM-powered clients.
---
Features
- List API Gateways in a given OCI compartment.
- Get details for a specific API Gateway.
- MCP stdio transport for easy integration with LLM agents and other clients.
- LlamaIndex/Ollama client for natural language interaction with OCI API Gateway resources.
---
Quickstart
1. Prerequisites
- Python 3.11 (required)
- uv (fast Python package/dependency manager)
- OCI account with API Gateway access
- OCI session authentication files (~/.oci/sessions/DEFAULT/token and oci_api_key.pem)
2. Install uv
curl -Ls https://astral.sh/uv/install.sh | sh
Or, from PyPI:
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



