Skip to main content
Glama

AutoTest AI β€” Model Context Protocol (MCP) Server

glama badge License: MIT

AutoTest AI is an industrial-grade defensive testing and refactoring engine embedded directly inside your AI IDE via the Model Context Protocol (MCP). It synthesizes parameterized boundary suites, audits cyclomatic branch depth, and flags missing exception boundaries with 96%+ branch coverage.

Native zero-friction support for Cursor, Claude Desktop, Windsurf, and any MCP-compliant client.


⚑ Features & MCP Tools

  1. generate_edge_tests:

    • Synthesizes production Pytest and Jest/Vitest test suites targeting mathematical extremes, empty/zero boundaries, type invariance, and fault injection.

    • Dual-tier synthesis:

      • Community (Free): Comprehensive boundary test suites and AST defensive auditing.

      • Enterprise Pro: Mutation fuzz matrices and invariant verification.

  2. audit_code_defenses:

    • Calculates AST cyclomatic complexity, branch depth, and identifies unhandled exception vectors.

  3. get_paywall_status:

    • Inspects active Web3 payment gateways, verified on-chain sponsorship wallets, and RPC endpoints.

  4. Zero-Overhead Native Execution:

    • Zero external third-party dependencies required. Starts in < 50ms, consumes < 15MB RAM.


Related MCP server: mcp-doctor

πŸš€ 1-Click Installation via Smithery CLI

Install directly into your IDE with a single command via Smithery:

For Cursor IDE:

npx -y @smithery/cli install @MaaBlock/autotest-mcp --client cursor

For Claude Desktop:

npx -y @smithery/cli install @MaaBlock/autotest-mcp --client claude

πŸ› οΈ Manual Configuration

1. Cursor IDE (.cursor/mcp.json)

Add the following to your workspace .cursor/mcp.json or global Cursor settings:

{
  "mcpServers": {
    "autotest": {
      "command": "python",
      "args": ["mcp_server.py"],
      "env": {
        "POLYGON_PAYOUT_ADDRESS": "0x267e548ab3444aa0a671914ac7c644306a6b90b4",
        "TRON_PAYOUT_ADDRESS": "TWvzvF4FszbXM6qnBS947aNJHfyvA1kdZC"
      }
    }
  }
}

2. Claude Desktop (claude_desktop_config.json)

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

  • Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "autotest": {
      "command": "python",
      "args": ["<PATH_TO_AUTOTEST_MCP>/mcp_server.py"],
      "env": {
        "POLYGON_PAYOUT_ADDRESS": "0x267e548ab3444aa0a671914ac7c644306a6b90b4",
        "TRON_PAYOUT_ADDRESS": "TWvzvF4FszbXM6qnBS947aNJHfyvA1kdZC"
      }
    }
  }
}

πŸ’‘ Usage in Chat

Ask Cursor or Claude:

"Use autotest to generate full edge-case unit tests for this function."

"Audit code defenses and cyclomatic complexity for the active file."


πŸ’Ž Web3 Paywall & Pro Upgrades

AutoTest AI operates on an autonomous Web3 freemium model:

  • Free Community Tier: Unlimited defensive test synthesis and complexity auditing.

  • Enterprise Pro Tier: Unlocks mutation fuzz matrices and property-based invariance testing.

  • Direct Paywall Gateway: https://autotest-ai.sweet-possum.workers.dev

  • Official Payout Addresses:


πŸ“œ License

Released under the MIT License. Copyright (c) 2026 AutoTest AI.

Available Tools

3 tools
audit_code_defensesA

Audits AST cyclomatic complexity, branch depth, and detects unhandled exception vectors in source code.

Inputs: code (required), language.

generate_edge_testsA

Synthesizes industrial-grade defensive unit tests with 96%+ branch coverage, boundary invariance, and exception handling for any source code.

Inputs: code (required), tier, tx_hash, language, +1 more.

get_paywall_statusA

Retrieves official sponsorship wallet addresses, live Web3 paywall gateway, and pro tier pricing.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool targets a clearly distinct action and resource: generating tests, auditing code defenses, and fetching paywall status. Even though get_paywall_status is unrelated to the testing domain, there is no ambiguity between the tools.

    Naming Consistency5/5

    All tool names follow a consistent snake_case verb_noun pattern: generate_edge_tests, audit_code_defenses, get_paywall_status. The naming convention is uniform and predictable.

    Tool Count4/5

    Three tools is a reasonable count and not excessive, but the inclusion of get_paywall_status feels tangential to the autotest theme, and two core tools is a slightly small surface for a testing/auditing server.

    Completeness2/5

    The server can generate tests and audit code defenses, but there are no tools to run tests, retrieve generated test outputs, manage configurations, or handle results. The paywall status tool is unrelated and does not fill these workflow gaps, leaving the domain only partially covered.

    Maintenance

    ActivityStale
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers