Testorax Mcp

Created By
Testoraxa month ago
Autonomous AI browser testing. Give Testorax a URL and it crawls your app, generates test scenarios, runs them in real browsers, and returns a bug report with screenshots. No test code to write. Works with any deployed web app.
Overview

It's a markdown editor — this is the full documentation page for your listing. Paste this:

# Testorax — AI Browser Testing

Testorax is your testing buddy. Give it the URL of any deployed web app and it crawls it, generates test scenarios using Orax AI, runs them in real Chromium browsers, and returns a structured bug report with per-step screenshots.

**No test code to write. No SDK to install. No CI config required.**

## What it does

- Crawls your app and discovers pages automatically
- Generates realistic user scenarios (login, checkout, forms, navigation)
- Executes them in real browsers with full diagnostic capture
- Returns a bug report with screenshots, error messages, and fix suggestions
- Pauses and asks you if it needs login credentials or gets stuck

## Setup

**Step 1 — Get your credentials**

1. Sign up at [testorax.com](https://testorax.com)
2. Go to `/account/api-key` to generate your API key (`ttx_...`)

**Step 2 — Configure the MCP server**

Add to your MCP client config:

```json
{
  "mcpServers": {
    "testorax": {
      "url": "https://testorax.com/mcp",
      "headers": {
        "X-Testorax-Email": "your@email.com",
        "Authorization": "Bearer ttx_your_api_key"
      }
    }
  }
}

Ready-made prompts

Copy these directly into your agent:

Run a test:

Run a full test on https://myapp.com using Testorax and give me the bug report

Quick scan:

Do a quick Testorax scan on https://myapp.com and summarize the findings

Debug a failure:

Use Testorax failure_context to explain why scenario [ID] failed in run [ID]

Retry failures:

Retry only the failed scenarios from Testorax run [ID]

Run a saved suite:

Run my Testorax saved suite [suite-name]

Available Tools

ToolDescription
create_bypass_runCreate a run with custom scenarios (requires API key)
run_statusGet live status of a run
get_reportFetch the full bug report
run_summary_mdGet a markdown summary optimized for LLM reading
failure_contextFull diagnostic context for a failed scenario
run_timelineChronological state timeline for a run
regressionsFind scenarios that just broke after a clean streak
retry_failedRe-run only failed scenarios from a previous run
cancel_runCancel a stuck or unwanted run
list_runsList recent runs
validate_scenariosDry-run validate scenario JSON before posting
get_scenario_schemaFetch the canonical scenario JSON schema
list_actionsList every supported step action with examples
get_run_statesRun state diagram and valid transitions
list_suitesList saved test suites
run_suiteTrigger a saved suite
list_variablesList saved variables
set_variableSave a variable for use in scenarios as ${NAME}
list_app_groupsList multi-URL test bundles
run_app_groupTrigger all URLs in an app group simultaneously
list_creditsList active promo codes and credits
get_dashboardAccount KPIs: pass rate, spend, top failures
list_messagesCheck for replies from the Testorax agent
send_messageAsk the human a question during a run
list_reposList connected GitHub repos
install_github_appGet the GitHub App install URL

Server Config

{
  "mcpServers": {
    "testorax": {
      "url": "https://testorax.com/mcp",
      "headers": {
        "X-Testorax-Email": "${TESTORAX_EMAIL}",
        "Authorization": "Bearer ${TESTORAX_API_KEY}"
      }
    }
  }
}
Project Info
Created At
a month ago
Updated At
a month ago
Author Name
Testorax
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Payai X402 Tools

2 hours ago
Payai X402 Tools

2 hours ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

a day ago