OCI Documentation MCP Server

Name: OCI Documentation MCP Server
Author: jin38324

@jin38324

Repository

About OCI Documentation MCP Server

Model Context Protocol (MCP) server for OCI Documentation

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

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

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is OCI Documentation MCP Server?

OCI Documentation MCP Server is a Model Context Protocol (MCP) server that provides tools to search for content and access Oracle Cloud Infrastructure (OCI) documentation. It is designed for developers and AI agents who need to programmatically find and read OCI documentation pages.

How to use OCI Documentation MCP Server?

Install the server via PyPI (uvx --from oci-documentation-mcp-server@latest python -m oci_documentation_mcp_server.server) or run locally from source with uv. Configure it in your MCP client with the desired transport (stdio, sse, or streamable-http). Use the --transport, --port, and --path arguments as needed. Set FASTMCP_LOG_LEVEL environment variable to ERROR to reduce log output.

Key features of OCI Documentation MCP Server

oci_search_documentation tool: searches Oracle Help Center and returns structured results.
oci_read_documentation tool: reads OCI documentation pages, converts HTML to Markdown.
Line‑based pagination for controlled reading of long documents.
Table of contents returned on the first read of a page.
In‑memory caching of converted pages (24 hours, up to 128 pages).
Supports stdio, SSE, and Streamable HTTP transports.

Use cases of OCI Documentation MCP Server

Searching OCI documentation for specific service names, error messages, or feature names.
Reading a documentation page in chunks to avoid flooding MCP responses.
Integrating OCI documentation lookup into AI‑powered assistants or automation workflows.
Programmatically retrieving table of contents and page content for offline processing.

FAQ from OCI Documentation MCP Server

What transports does OCI Documentation MCP Server support?

It supports stdio, sse, and streamable-http transports (as of 2026-05-20).

Which search engine does OCI Documentation MCP Server use?

It uses the Oracle Help Center Search API (changed from a previous engine on 2026-05-19).

How is documentation content cached?

Converted pages are cached in process memory for 24 hours, up to 128 pages. The cache stores a single line‑list representation to avoid duplicating full Markdown text.

What URL restrictions apply to `oci_read_documentation`?

The URL must be from docs.oracle.com and must end with .htm or .html.

What is the default search result limit?

The default limit for oci_search_documentation is 3 results. You can override it with the limit parameter.

Comments

More Memory & Knowledge MCP servers

JupyterMCP - Jupyter Notebook Model Context Protocol Integration

jjsantos01

A Model Context Protocol (MCP) for Jupyter Notebook

130

Notion MCP Server

awkoy

Notion MCP server for Claude, Cursor, ChatGPT & Claude Desktop. Connect AI agents to Notion via Model Context Protocol — pages, databases, blocks, comments, files.

159