ibm-openpages-local

An experimental local Model Context Protocol (MCP) server that enables AI agents to securely interact with IBM OpenPages GRC platform through a standardized interface.

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio ibm-ibm-openpages-local-mcp-server python start_mcp.py \
  --env HOST="server host (default 0.0.0.0)" \
  --env PORT="server port (default 8000)" \
  --env DEBUG="True or False" \
  --env LOG_LEVEL="INFO, DEBUG, WARNING, or ERROR" \
  --env SSL_VERIFY="True or False" \
  --env OPENPAGES_APIKEY="API key for bearer authentication" \
  --env OPENPAGES_BASE_URL="URL to your OpenPages instance (e.g., https://openpages.example.com)" \
  --env OPENPAGES_PASSWORD="password for basic authentication" \
  --env OPENPAGES_USERNAME="username for basic authentication" \
  --env OPENPAGES_AUTHENTICATION_URL="token URL for bearer authentication" \
  --env OPENPAGES_AUTHENTICATION_TYPE="basic or bearer"

How to use

This MCP server implements the Model Context Protocol to interact with an IBM OpenPages GRC instance via STDIO using JSON-RPC. It dynamically exposes CRUD-style tools for OpenPages object types (such as Issues, Controls, Risks) based on a JSON configuration. Agents can discover available tools, inspect their parameters, and issue create, read, update, or delete operations through standardized JSON-RPC requests. The server handles authentication to OpenPages and provides a consistent interface so agents like watsonx assistant, Claude Desktop, or other MCP-enabled clients can securely operate on OpenPages data from a local environment.

How to install

Prerequisites:

Python 3.11+ installed on your machine
Git to clone the repository
Access to an IBM OpenPages instance (or test instance) for authentication

Install steps:

Clone the repository and change into the project directory:

git clone https://github.com/IBM/ibm-openpages-local-mcp-server
cd ibm-openpages-local-mcp-server

Create and activate a Python virtual environment: On macOS/Linux:

python3 -m venv venv
source venv/bin/activate

On Windows:

python -m venv venv
venv\Scripts\activate

Install dependencies:

pip install -r requirements.txt

Copy and configure environment variables:

cp .env.example .env

Edit the resulting .env file with your OpenPages connection details (or populate the environment variables as described in the mcp_config).

Start the MCP server:

python start_mcp.py

Optional for debugging:

python start_mcp.py --debug

Additional notes

Tips and common considerations:

Ensure OPENPAGES_BASE_URL points to a reachable OpenPages instance and that authentication credentials are correct.
Set SSL_VERIFY to False only in development or trusted environments; enable SSL verification for production deployments.
The server is designed to be extended via object_types.json; to add support for a new OpenPages object type, update the configuration and restart the server.
If you encounter connection or authentication errors, check the environment variables in the running process and review LOG_LEVEL for detailed logs.
The MCP server communicates with AI agents via STDIO and JSON-RPC; use tools/list to discover available operations before performing CRUD actions.

Related MCP Servers

mcp-vegalite

MCP server from isaacwasserman/mcp-vegalite-server

github-chat

A Model Context Protocol (MCP) for analyzing and querying GitHub repositories using the GitHub Chat API.

nautex

MCP server for guiding Coding Agents via end-to-end requirements to implementation plan pipeline

pagerduty

PagerDuty's official local MCP (Model Context Protocol) server which provides tools to interact with your PagerDuty account directly from your MCP-enabled client.

futu-stock

mcp server for futuniuniu stock

mcp -boilerplate

Boilerplate using one of the 'better' ways to build MCP Servers. Written using FastMCP