Enables automatic generation of edge-case and boundary test suites for JavaScript/TypeScript projects using Jest.
Enables automatic generation of edge-case and boundary test suites for Python projects using Pytest, along with AST-based defensive auditing.
Enables automatic generation of edge-case and boundary test suites for JavaScript/TypeScript projects using Vitest.
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.
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.
audit_code_defenses:
Calculates AST cyclomatic complexity, branch depth, and identifies unhandled exception vectors.
get_paywall_status:
Inspects active Web3 payment gateways, verified on-chain sponsorship wallets, and RPC endpoints.
Zero-Overhead Native Execution:
Zero external third-party dependencies required. Starts in < 50ms, consumes < 15MB RAM.
Related MCP server: mcp-doctor
Install directly into your IDE with a single command via Smithery:
npx -y @smithery/cli install @MaaBlock/autotest-mcp --client cursornpx -y @smithery/cli install @MaaBlock/autotest-mcp --client claude.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"
}
}
}
}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"
}
}
}
}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."
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:
Polygon (ERC-20 USDC): 0x267e548ab3444aa0a671914ac7c644306a6b90b4 (View on PolygonScan)
TRON (TRC-20 USDT): TWvzvF4FszbXM6qnBS947aNJHfyvA1kdZC (View on TronScan)
Released under the MIT License. Copyright (c) 2026 AutoTest AI.
Audits AST cyclomatic complexity, branch depth, and detects unhandled exception vectors in source code.
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | The source code to inspect | |
| language | No | Programming language | python |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of disclosure. It accurately conveys the static-analysis nature (auditing and detecting) and the specific analysis dimensions. However, it does not explicitly state that the tool is non-mutating, whether it accesses external resources, or what the output format is. 'Audit' strongly implies read-only, so this is adequate but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, tight sentence that front-loads the primary action and lists concrete audit dimensions. There is no redundancy, and every clause adds specific value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple two-parameter tool, the description is reasonably complete. However, with no output schema and no annotations, it does not describe what the agent should expect as a return value, how results are structured, or whether certain languages are unsupported. This leaves an agent to discover behavior at runtime.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so both parameters are already documented ('The source code to inspect' and 'Programming language'). The description adds little beyond the schema, though it gives context for why language matters (AST parsing). Baseline 3 is appropriate for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb ('Audits') and clearly identifies the resource (source code) and the exact dimensions being analyzed (AST cyclomatic complexity, branch depth, unhandled exception vectors). It is easily distinguishable from sibling tools like generate_edge_tests and get_paywall_status.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when code quality and exception-safety analysis is needed, but it does not explicitly state when to use this tool versus alternatives, nor does it provide exclusion criteria or prerequisites. No when-not guidance is present.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Synthesizes industrial-grade defensive unit tests with 96%+ branch coverage, boundary invariance, and exception handling for any source code.
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | The source code snippet or function to test | |
| tier | No | Test synthesis tier: 'community' (free) or 'pro' (mutation fuzzing) | community |
| tx_hash | No | Optional Polygon or TRON transaction hash verifying 1 USDC/USDT fee for pro tier | |
| language | No | Programming language (python, typescript, javascript) | python |
| framework | No | Target test framework (pytest, jest, vitest) | pytest |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavioral disclosure burden. It discloses some output quality traits (coverage, boundary, exception handling), but it fails to mention the pro-tier payment requirement and tx_hash verification, which is a significant behavioral cost, and it overclaims 'any source code' despite the schema's restricted language/framework enums.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence that front-loads the verb and resource, then packs relevant quality constraints into a compact list. No wasted sentences or redundant restatements of the tool name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 5-parameter tool with no output schema and no annotations, this description is incomplete. It omits what the tool returns, how tier/tx_hash affect behavior, and what language/framework limitations apply, leaving an agent without enough context to invoke it safely and correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3 even without parameter details in the description. The description adds no parameter-level guidance and its 'any source code' claim is arguably inconsistent with the language enum, but the schema itself documents every parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific verb ('Synthesizes') and resource ('unit tests') and enriches it with concrete qualities: 96%+ branch coverage, boundary invariance, and exception handling. This clearly separates it from sibling tools like audit_code_defenses and get_paywall_status, which concern auditing and paywall status rather than test generation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It states the intended use case ('for any source code') and the action (synthesize tests), so an agent can infer when to choose it. It does not explicitly name alternatives or conditions when not to use it, but the sibling tools are sufficiently distinct.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieves official sponsorship wallet addresses, live Web3 paywall gateway, and pro tier pricing.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden. It discloses a read behavior via 'Retrieves' but gives no detail on response format, data freshness, authentication, or failure behavior. For a zero-parameter getter this is serviceable, though not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no filler, front-loading the action and listing the specific data items returned. Every word contributes to understanding what the tool does.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with no parameters and no output schema, and the description enumerates the data domains returned. It does not specify the exact return shape, but for an unparameterized getter this is adequate. An agent can invoke the tool without missing required information.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema is empty and schema description coverage is 100%, so parameter semantics are trivially satisfied. The description correctly does not dwell on parameters because there are none. The baseline of 4 applies for zero-parameter tools.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the specific verb 'Retrieves' and names exact resources: sponsorship wallet addresses, live Web3 paywall gateway, and pro tier pricing. This distinguishes it from siblings like generate_edge_tests and audit_code_defenses. Minor ambiguity remains because 'status' is not explicitly defined, but the tool's scope is still clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or alternative guidance is provided; the description only states what it retrieves. The intended context is inferable: call when paywall status, sponsorship, or pricing information is needed. Siblings are unrelated, so there are no competing choices that need disambiguation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0audit_code_defensesgenerate_edge_testsget_paywall_statusScored across 3 tools
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.
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.
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.
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.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Hosted Amazon Seller and Vendor MCP server for Claude, ChatGPT, Cursor, Codex, Gemini, Copilot.
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/MaaBlock/autotest-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
