Skip to content
MCP server

Ai Test Process MCP

MCP server that helps draft, review and analyze JSTQB-based test plans and test designs

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI, self-hosted, API
Runs
Locally
Version
0.39.2
Listing updated
today

Similar MCP servers

About Ai Test Process MCP

Ai Test Process MCP is an open-source MCP server for developer tools. It runs locally on your machine and is started by your AI client.

The README says this server is built to support the work inside each stage of the JSTQB Generic Test Process rather than to operate a test management tool. Its current scope covers test planning, test analysis and test design, with a stated roadmap to extend the remaining stages later.

It exposes tools that generate a Japanese test plan draft structured around a 15-chapter JSTQB-style template, review an existing plan for structural gaps, and apply mechanical fixes such as normalizing placeholder text. Test design support includes boundary value, equivalence partitioning, decision table and pairwise case generation, plus exploratory charter design.

The package is published on npm and runs over stdio, so it is intended for developers and QA practitioners who use an MCP-capable AI client such as Claude Desktop or Claude Code.

Install

Run in a terminal

claude mcp add ai-test-process-mcp -- npx -y ai-test-process-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "ai-test-process-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ai-test-process-mcp"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "ai-test-process-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ai-test-process-mcp"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "ai-test-process-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "ai-test-process-mcp"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "ai-test-process-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ai-test-process-mcp"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "ai-test-process-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ai-test-process-mcp"
      ]
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Tools this server provides (11)

Taken from the project documentation; the running server may differ.

create_test_plan
Generates a JSTQB-aligned test plan draft in Japanese Markdown.
review_test_plan
Reviews a test plan for structural gaps and returns a checklist for semantic review.
revise_test_plan
Applies mechanical fixes to a test plan and lists remaining required gaps.
design_boundary_values
Enumerates boundary values with valid and invalid judgments.
design_equivalence_partitioning
Generates representative test cases from equivalence classes.
design_decision_table
Enumerates and compresses decision table rules and reports coverage.
design_pairwise
Generates pairwise combination tables from factors and forbidden combinations.
generate_test_cases
Derives test case specifications from test conditions with coverage checks.
generate_exploratory_charters
Generates exploratory test charter tables and checks them.
review_test_specification
Evaluates a test specification against test basis documents.
analyze_requirements
Analyzes requirement documents for ID structure, ambiguity and boundary candidates.

What it does

Japanese test plan drafting
Generates a Markdown test plan draft in Japanese from project inputs, marking unfilled items explicitly.
Test plan review and revision
Checks a plan for missing chapters and required fields, then returns a revised version and a list of remaining gaps.
Black-box test design techniques
Derives boundary values, equivalence classes, decision tables and pairwise combinations deterministically.
Exploratory test charters
Produces charter tables with time boxes and checks them for missing or mismatched coverage.
Requirements and specification audits
Analyzes requirement IDs, ambiguous wording and coverage links across test basis documents.

Good for

  • Drafting a Japanese test plan from a project scope and risk list
  • Reviewing an existing test plan for missing JSTQB chapters
  • Generating boundary value and equivalence test cases from a specification
  • Checking a test specification for requirement coverage gaps

Pricing

Open source

Ai Test Process MCP FAQ

How is the server installed?

The README says it is published on npm and can be started with npx using the package name ai-test-process-mcp@latest, with Node.js 18 or later required.

Does it require an API key or environment variables?

The registry entry lists no environment variables for the npm package.

Which language are the generated test plans in?

The README states that create_test_plan produces the test plan draft in Japanese Markdown.

Is Ai Test Process MCP free?

Yes. Ai Test Process MCP is open source, so you can use and self-host it for free.

How do I add Ai Test Process MCP to Claude Code?

Run this command in your terminal: claude mcp add ai-test-process-mcp -- npx -y ai-test-process-mcp

What are the best alternatives to Ai Test Process MCP?

The closest alternatives to Ai Test Process MCP are Testing, Testiny Test Management, Qase Test Management, Api Testing MCP and Testdino MCP.

Where this comes from

  • Description: written from the project's README and its MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers