MCP integration

This section describes how to control OpenText Enterprise Performance Engineering through external AI tools using the Model Context Protocol (MCP).

Tip: See the Video gallery for a video on MCP server enhancements.

About MCP

The Model Context Protocol (MCP) is an open standard that enables AI assistants to connect securely with external tools and data sources. When you make a natural language request, such as "Run the demo script test in project XYZ", the MCP client translates the request into the protocol format and sends it to the MCP server. The MCP server applies security checks, performs the requested operation, and returns the result.

This natural language approach eliminates the need to remember specific IDs, navigate multiple UI screens, or write API scripts. Just describe what you need, and the AI tool handles the technical details.

MCP server capabilities

The MCP integration supports over 20 tools, enabling comprehensive test management and monitoring through natural language.

The supported tools provide the following capabilities.

Area Capabilities
Project management

  • Get current domain and user configured in the system

  • Get all domains available to the user

  • Get all projects on current domain available to the user

  • Change current domain and project
Test configuration

  • Get all tests in the project

  • Get all test sets

  • Get all scripts in the project

  • Get all test folders in the project

  • Get load test details

  • Check test validity

Versions 26.3 and later:

  • Create and manage test sets and test set folders.
Test execution

  • Start new test run

  • Stop test run

Note:

  • Only basic workload by test by number can be defined.

  • Automatch load generators will be used.

  • Default runtime settings for the protocol are defined.

  • Vusers will start and stop simultaneously.
Results & monitoring

  • Get all runs of a specific test

  • Get active runs of a specific test

  • Get test run status, get test run results

  • Get online summary data

  • Get extended run data

  • Download test run results

  • Start late analysis

  • Post-run action parameter can be defined during Start Run/Stop run

Versions 26.3 and later:

  • Download trend reports, HTML reports, and resources in parts for reliable transfer in AI-assisted workflows.

  • Create consolidated custom PDF reports from selected report sections.
Host management Get list of hosts available in the project

Each tool corresponds to a single public API operation, making it easy to chain operations together for complex workflows.

Integrate with the MCP server

This section explains how to integrate with the MCP server.

To integrate with the MCP server:

  1. Prerequisite. An external AI tool must be installed and configured. For example, Claude Desktop application.

  2. Install the MCP server.

    1. Copy the MCP server installer from <server_Installdir>\Additional Components\MCPServer to the local machine where your AI tool is installed.

      Note: MCP Server is also available from Download Applications. For details, see Download applications and components.

    2. Run the installer to complete the MCP server setup.

  3. Configure the connection.

    1. In the MCP Server Connection Configuration window, provide the following OpenText Enterprise Performance Engineering details:

      • Server URL

      • Client ID

      • Client Secret

      • Domain

      • Project

      • (Optional) Tenant ID

    2. Click Save to confirm connectivity and close the window.

  4. Update the AI tool configuration.

    Add the MCP server to the tool’s MCP configuration file (commonly mcp.json; some tools use alternatives such as claude_desktop_config.json). The file name and location depend on the tool.

    Example structure to add:

    Copy code 
    {
      "mcpServers": {
        "OT Enterprise Performance Engineering MCPServer": {
          "command": "C:\\{MCP_Server_Installation_Root}\\EnterprisePerformanceEngineering_MCPServer.exe",
          "args": ["--silent"]
        }
      }
    }

  5. Registration.

    The MCP server registers automatically with the external AI tool and exposes OpenText Enterprise Performance Engineering tools.

    Note: All connection-related data is stored encrypted.

Network security configuration

To mitigate Server-Side Request Forgery (SSRF) risks, the MCP server includes a NetworkSecurity section in its configuration.

Use this section to control which hosts can be accessed and enforce security rules, while allowing flexibility for internal or development scenarios.

Key settings Details
AllowedHosts

Define the host names that the MCP server can call (exact names and wild cards are supported).

Recommended: Restrict access to your hosts to minimize exposure.
AllowHttp

Controls whether plain HTTP is permitted. If set to true, both HTTP and HTTPS are allowed.

Recommended: Set to false (the default value) so that only HTTPS is allowed.
AllowPrivateIPs

Blocks or permits private/internal IP ranges and IPv6 internal ranges.

Recommended: Set to false to block private networks unless they are explicitly listed in AllowedHosts.

URL validation rules

The following rules ensure that all server URLs are properly validated for security and connectivity before being used by the MCP server.

Area Details
General URLs must be valid and absolute.
Scheme restrictions

  • By default, only HTTPS URLs are allowed.

  • If AllowHttp = true, both HTTP and HTTPS are allowed.

  • Any other scheme, such as FTP or file, is rejected.
Host validation The host must exist and be reachable using DNS.
Private IP restrictions

  • Private IPs are blocked unless explicitly allowed.

    Example of private IPs: 10.x.x.x, 192.168.x.x, 172.16–31.x.x.

  • Private IPs are allowed only if:

    • Listed in AllowedHosts, or

    • AllowPrivateIPs = true

  • A private IP explicitly listed in AllowedHosts overrides AllowPrivateIPs = false.
Allowed hosts

  • Only explicitly allowed hosts or "*" for public hosts are accepted (public hosts are not recommended for production).

  • Wildcards (*.example.com) are supported for subdomains.

  • Host names in AllowedHosts must not include protocol prefixes.

  • If a host is not allowed and not covered by "*", it is blocked.

Report enhancements using AI

Available in versions: 26.3 and later

This section describes how AI clients can use trend reports, HTML reports, and custom PDF generation.

Note:

  • Retrieving and processing report data can take time, depending on report size and the AI client implementation. AI processing may also increase token usage in the AI solution.

  • Reporting output depends on the AI solution you use. OpenText Enterprise Performance Engineering and the MCP server provide the data and tool actions, but the AI solution determines how that data is interpreted, structured, and presented. The final output, including format, structure, and analytical depth, may vary and is outside the control of OpenText or the MCP server.

Reports are downloaded in chunked mode

This flow improves reliability when AI clients retrieve large report data.

  • Trend reports. Trend report data is downloaded in parts, helping AI clients avoid payload limits that can occur in some environments. For example, some AI clients enforce payload limits of around 1 MB. By transferring the data in parts, AI clients can retrieve complete trend data more reliably and continue with analysis and report generation.

  • HTML reports. When an AI client requests an HTML report, OpenText Enterprise Performance Engineering provides the original HTML report package from the server. The package is downloaded in parts to improve reliability. After downloading, the AI client can generate a standalone HTML report that is easy to review and share, or create a custom report based on the user's request using the original package.

Create custom reports using AI

You can use your AI assistant to build a consolidated PDF report from selected report content and related trend reports.

The enhanced reporting capabilities make report creation more flexible and practical for day-to-day analysis. You can combine run content and related trend reports, reduce manual editing, and refine the output through follow-up prompts.

  • Faster report generation. Create consolidated PDF reports from selected run report sections and related trend reports without assembling the content manually.

  • More flexibility. Select the sections, headers, and trend reports to include, then refine the output with prompts such as filtering transaction groups or adjusting severity thresholds.

  • Better day-to-day productivity. Use AI-assisted flows to turn raw run data into a clearer report that is easier to review, share, and discuss with others.

  • Reliable large-output handling. Use chunked report downloads to improve transfer reliability when working with large files.

You can also use trend data to generate regression-focused reports and then refine the same report with follow-up prompts.

To create a custom report using AI:

  1. Ask the AI assistant to download the run report in HTML format.

  2. Select the report sections that you want to include in the final PDF.

  3. Select whether to include section headers.

  4. Select the related trend reports that you want to include.

  5. Ask the AI assistant to generate the consolidated PDF report.

  6. Refine the generated report with follow-up prompts to add sections, modify existing content, or remove sections that are no longer relevant. For example:

    • "Filter the report to failed transactions only and increase the severity threshold for warning items."

    • "Create a PDF report with all transactions that have regression, sorted from worst to least severe."

    • "Create a similar report, but only for transactions in the Execute Load Test area, and update all fields accordingly."

    • "For the last report, use three regression thresholds: Major >= 50%, Moderate 5-49%, Minor < 5%."

Note: The generated PDF can include only the sections and trend reports that you selected. Header and footer areas in the source content may be cropped in the final PDF output.

Usage examples

The following are examples of creating, running, and managing tests using natural language.

Example 1: Create a Test

Example Command Steps
“Create a new performance test.”

  1. The AI tool shows the available scripts and hosts.

  2. Select a folder for the test.

  3. Provide a test set name. If a test set does not exist, a new one is created.

  4. Select the workload type: Basic workload only, by test or by number.

  5. Define the groups (scripts) to use and enter the number of Vusers to allocate to each script. For example, 10 Vusers for every script in the folder.

  6. Define the duration of the scheduler for the entire test. This includes Vuser initialization, start, and stop time. For example 30m or 1h.

  7. Assign Automatch Controller and load generators.

  8. Choose load generator placement: per test or per group.

  9. The test is created and ready to run.

Example 2: Run a Test

Example Commands Steps

  • “Show me all tests in the project.”

  • “Show me details of test 1011.”

  • “Run test Checkout.”

  1. The AI tool lists the available tests (Name, ID, Location).

  2. Select a test by name or ID.

  3. The AI tool validates the test.

  4. Choose a test set from the list.

  5. Choose a post-run action, such as download report.

  6. The test starts and the AI tool returns the Run ID.

Example 3: Manage test runs

Example Commands Capabilities

  • “List runs for Checkout.”

  • “Show active runs.”

  • “Stop run 9722.”

  • View the list of runs for a specific test, including run ID, state, and start time.

  • View details of active runs, including run ID, test name, start time, and duration.

  • To stop an active run, provide the run ID. If you do not provide the run ID, the AI tool prompts you to choose a post run action.

  • Start late analysis.

  • Get online summary or extended run data.

  • Download results. For example, reports.zip.

Example 4: Manage test sets and test set folders

Example Commands Capabilities

  • “List all test sets.”

  • “List all test set folders.”

  • “Create a test set folder named Quarterly_Release under Performance Tests.”

  • “Create a test set named Checkout_Regression in Performance_Release.”

  • View existing test sets in the current project context

  • View existing test set folders in the current project context

  • Create and organize test set folders to keep related runs grouped by release or feature area.

  • Create test sets through the AI workflow and continue with run preparation.