oci-documentation-mcp-server

oci-documentation-mcp-server

2

The OCI Documentation MCP Server is a Model Context Protocol server aimed at accessing and searching OCI documentation. It provides tools to fetch and convert documentation pages to markdown as well as search through the documentation effectively.

Inspired by: https://github.com/awslabs/mcp/tree/main/src/aws-documentation-mcp-server

OCI Documentation MCP Server

Model Context Protocol (MCP) server for OCI Documentation

This MCP server provides tools to search for content, and access OCI documentation.

Features

  • Read Documentation: Fetch and convert OCI documentation pages to markdown format
  • Search Documentation: Search OCI documentation using search engine

Prerequisites

Installation Requirements

  1. Install uv from Astral or the GitHub README
  2. Install Python 3.10 or newer using uv python install 3.10 (or a more recent version)

Installation

MCP config:

{
  "mcpServers": {
    "oci-documentation-mcp-server": {
        "command": "uvx",
        "args": ["oci-documentation-mcp-server@latest"],
        "env": {
          "FASTMCP_LOG_LEVEL": "ERROR"
        },
        "disabled": false,
        "autoApprove": []
    }
  }
}

It may be a little more complicated on Windows:

{
  "mcpServers": {
      "oci-documentation-mcp-server": {
        "command": "uvx",
        "args": [
          "--from",
          "oci-documentation-mcp-server@latest",
          "python",
          "-m",
          "oci_documentation_mcp_server.server"
        ],
        "env": {
          "FASTMCP_LOG_LEVEL": "ERROR"
        },
        "disabled": false,
        "autoApprove": []
    },
  }
}

Basic Usage

Example:

  • In Cursor ask: Write a function to download files for OCI Object Storage.

Cursor_MCP

Tools

read_documentation

Fetches an OCI documentation page and converts it to markdown format.

read_documentation(url: str) -> str

search_documentation

Searches OCI documentation using the search engine.

search_documentation(search_phrase: str, limit: int) -> list[dict]