PromptBrake Free Tools

Free MCP tools for prompt-injection test inputs, OWASP LLM risk mapping, AI release planning, and custom response test-pack creation for PromptBrake CI.

View on promptbrake.comTry this MCPSponsored

Hosted MCP Server

npx add-mcp 'https://promptbrake.com/free-tools/mcp'

Installs into Claude Code, Codex, Cursor and more

Documentation

Free AI Security and ADLC Tools | PromptBrake

Source: https://promptbrake.com/free-tools Summary: Free AI testing tools: build custom AI test cases for CI, plan an agent release, review chatbot safety, and explore prompt injection and OWASP test examples.

Free Tools

Free AI security tools for teams shipping agents, APIs, and chatbots

Build custom AI response tests for CI, create an ADLC release plan, review chatbot launch readiness, and turn OWASP-aligned guidance into concrete test cases.

Free · No signup

Run these free tools inside your AI agent

One read-only MCP server works with Claude, ChatGPT, Cursor, and other MCP clients. No PromptBrake account or API key required. Tool inputs and results are not stored; operational request metadata is logged. See our privacy policy.

Server URL https://promptbrake.com/free-tools/mcp

Claude

  1. Open Settings → Connectors
  2. Choose Add custom connector
  3. Paste the server URL

ChatGPT

  1. Open Settings → Connectors → Advanced and turn on Developer mode
  2. Choose Create to add a connector
  3. Paste the server URL and set authentication to None

Claude Code and Cursor

Claude Code, in your terminal:

claude mcp add --transport http promptbrake-free-tools https://promptbrake.com/free-tools/mcp

Cursor: add a remote MCP server with the same URL.

Then ask, for example: “Get the persona prompt injection payloads” or “Build a test pack for my refund chatbot.” Tools: prompt injection payloads, OWASP LLM mapper, ADLC release planner, and AI test case builder. Use them only on chatbots and APIs you own or are authorized to test.

Give your AI assistant a workflow for all four free tools

The PromptBrake skill guides your assistant through prompt-injection inputs, OWASP LLM risk mapping, AI release planning, and custom response test packs.

With Node.js installed, run this in your project and choose your supported assistant:

npx skills add AJ888/promptbrake-skills --skill promptbrake-free-tools

Connect the MCP server above separately. Your client must support both skills and remote MCP. The skill prepares test inputs and plans; running tests requires a configured PromptBrake runner and CI access. Text checks do not verify backend actions.

View the skill, examples, and manual installation instructions →

AI Test Case Builder

Write your own response checks, download a test file, and run it alongside PromptBrake's security checks in CI.

Build your AI tests →

ADLC Release Readiness Planner

Define an AI agent's authority boundaries, human approvals, release blockers, evidence requirements, rollback controls, and starter PromptBrake gate policy.

Build an ADLC release plan →

AI Chatbot Safety Checklist

Review scope, brand promises, human handoff rules, customer data boundaries, and retest discipline before your chatbot goes live.

Open chatbot checklist →

LLM Security Checklist

Use a practical release checklist covering prompt injection, tool permissions, data exposure, output controls, and rerun discipline.

Open checklist →

Prompt Injection Payload Library

Copy direct, indirect, and multi-turn prompt injection examples you can adapt for controlled testing.

Open payload library →

OWASP LLM Test Case Mapper

Translate broad OWASP-style risk categories into concrete test ideas and ownership decisions for your team.

Open test case mapper →

Next Step

Use the free tools to prepare. Use PromptBrake to verify.

The tools help you think through risk. PromptBrake runs the attacks against the endpoint you actually ship and gives you evidence-backed findings.

Read prompt injection examples and payloads → Read the LLM security testing guide →

Planning

Build a checklist, collect payloads, and map your gaps before release.

Testing

Run 138 adversarial checks across 18 attack categories against your real AI API endpoint or customer-facing chatbot.

Proof

Review internal reference app results showing a score move from 75 to 91 after remediation.

Run chatbot launch testing → Review private enterprise testing → See sample test results → Read the chatbot launch guide → Read the ADLC release guide → View pricing →