Agent Onboarding

Everything you need to onboard your AI agent to bugAgent.

If you're developing with AI, bugAgent offers several resources to improve your experience. Whether your agent is an autonomous coding assistant, a CI/CD bot, or a custom workflow — bugAgent gives it the ability to file, classify, and manage bugs without human intervention.

Prerequisites

Before your AI agent can start filing bugs, you'll need a human to complete a one-time setup:

Create a bugAgent account

A human needs to sign up for a bugAgent account. This takes less than a minute.

Create an API Key

From the dashboard settings, generate an API key. This is what your agent uses to authenticate. The full key is shown only once — save it securely.

Give the key to your agent

Set the key as an environment variable or pass it via config. Your agent can now create bug reports, query reports, manage projects, and more.

💡

The Free tier includes unlimited bug reports and test cases — no limits, no credit card required.

Free Tier

Every bugAgent account starts on the Free plan. Your agent gets access to:

Unlimited bug reports with auto-classification

AI-powered classification — type, severity, and confidence scoring

1 project to organize your reports

Full MCP server access — all 27 tools available

REST API access — same endpoints as the Team plan

Usage analytics — daily counts and breakdowns

1 API key for authentication

Dashboard access to review and manage reports

Need more? View Team and Enterprise plans for higher limits, Jira sync, team features, and priority support.

bugAgent MCP Server

The bugAgent MCP server connects your AI agent to bugAgent via the Model Context Protocol. It runs locally alongside your AI client and gives your agent direct access to:

🐛

Bug Report Management

Create, list, get, update, and classify bug reports. Auto-classification enriches every report with type, severity, and confidence score.

📁

Project Management

Create and manage projects. File bugs into specific projects for organized tracking across multiple codebases.

📊

Analytics & Usage

Check usage limits, view statistics, and get breakdowns by type, severity, and status. Your agent can monitor its own quota.

🔑

API Key Management

Generate, list, regenerate, and revoke API keys programmatically. Rotate credentials without human intervention.

🎯

Jira Integration

Sync bug reports to Jira with mapped fields, priority, and labels. Bridge AI-discovered bugs directly into your team's workflow.

👤

Account & Profile

Setup

Add bugAgent to your MCP client configuration. Here are examples for popular clients:

claude mcp add bugagent -- npx -y @bugagent/mcp-server

Then set your API key:

export BUGAGENT_API_KEY=ba_live_your_key_here

// .cursor/mcp.json
{
  "mcpServers": {
    "bugagent": {
      "command": "npx",
      "args": ["-y", "@bugagent/mcp-server"],
      "env": {
        "BUGAGENT_API_KEY": "ba_live_your_key_here"
      }
    }
  }
}

// Add to your Codex MCP configuration
{
  "mcpServers": {
    "bugagent": {
      "command": "npx",
      "args": ["-y", "@bugagent/mcp-server"],
      "env": {
        "BUGAGENT_API_KEY": "ba_live_your_key_here"
      }
    }
  }
}

{
  "mcpServers": {
    "bugagent": {
      "command": "npx",
      "args": ["-y", "@bugagent/mcp-server"],
      "env": {
        "BUGAGENT_API_KEY": "ba_live_your_key_here"
      }
    }
  }
}

Replace ba_live_your_key_here with your actual API key from the console.

Selective Tools

You can selectively enable specific tools using the --tools argument. This is useful if you want to limit what your agent can do:

npx @bugagent/mcp-server --tools create_bug_report,list_bug_reports,get_usage

Only the specified tools will be available to the MCP client. Omit --tools to enable all 27 tools.

Available MCP Tools

The bugAgent MCP server provides 27 tools across 7 categories:

Bug Report Management

create_bug_report File a new bug report. Auto-classifies bug type if not provided.

list_bug_reports List bug reports with optional filters by type, severity, or search query.

get_bug_report Get full details of a specific bug report by ID.

update_bug_report Update an existing bug report. Only provided fields will be changed.

classify_bug Classify a description into a bug type with confidence score.

flush_reports Bulk delete old bug reports. Admin only.

Usage & Analytics

get_usage Check current usage against plan limits and remaining quota.

get_stats Get daily counts, breakdowns by type, severity, and status.

Project Management

list_projects List available projects with names, slugs, and default status.

create_project Create a new project. First project becomes the default.

delete_project Delete a project. Choose how to handle its bug reports.

Authentication & Account

register_account Create a new account with email and password.

login Sign in and receive access tokens.

update_profile Update your display name.

change_password Change your account password.

get_settings Get profile info, plan, and notification preferences.

update_settings Update notification preferences.

API Key Management

generate_api_key Create a named API key. Full key shown only once.

list_api_keys List active keys. Shows prefix only, never the full key.

regenerate_api_key Revoke and replace a key with the same name and scopes.

delete_api_key Revoke and delete a key. Stops working immediately.

Integrations

sync_to_jira Sync a report to Jira with mapped fields, priority, and labels.

upgrade_plan Upgrade subscription. Returns a Stripe checkout URL.

Automation

list_automations List Playwright automation scripts. Filter by project_id or status (draft/active/paused).

get_automation Get full automation details including Playwright script and recent runs.

run_automation Trigger an immediate Playwright test run in headless Chromium. Returns run_id and status.

list_automation_runs List recent runs for an automation with status, duration, and errors.

bugAgent Skills

Skills give AI agents specialized knowledge for specific tasks. Install the bugAgent skill to give your coding assistant full bug reporting capabilities:

claude skills install bugagent --from @bugagent/mcp-server

# In Cursor, add to .cursor/mcp.json:
{
  "mcpServers": {
    "bugagent": {
      "command": "npx",
      "args": ["-y", "@bugagent/mcp-server"],
      "env": { "BUGAGENT_API_KEY": "ba_live_your_key_here" }
    }
  }
}

# In Codex, add bugAgent as an MCP server:
{
  "mcpServers": {
    "bugagent": {
      "command": "npx",
      "args": ["-y", "@bugagent/mcp-server"],
      "env": { "BUGAGENT_API_KEY": "ba_live_your_key_here" }
    }
  }
}

git clone https://github.com/TestLauncher/bugAgent.git
cd bugAgent/mcp-server
npm install
npm run build

Then set your API key:

export BUGAGENT_API_KEY=ba_live_your_key_here

Quick Start for Agents

Create a bug report programmatically using the REST API:

Python

import requests

API_KEY = "ba_live_your_key_here"
BASE_URL = "https://app.bugagent.com/api"

response = requests.post(
    f"{BASE_URL}/reports",
    headers={
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json"
    },
    json={
        "title": "Checkout fails with 500 on discount code",
        "description": "Applying SAVE20 at checkout returns HTTP 500. "
                       "Affects all users. Stripe webhook not triggered. "
                       "Steps: 1. Add item to cart, 2. Enter code SAVE20, "
                       "3. Click Apply. Expected: discount applied, order completes. "
                       "Actual: 500 Internal Server Error.",
        "severity": "critical"
    }
)

report = response.json()
print(f"Bug filed: {report['id']} — {report['type']} ({report['severity']})")

TypeScript

const API_KEY = "ba_live_your_key_here";
const BASE_URL = "https://app.bugagent.com/api";

const response = await fetch(`${BASE_URL}/reports`, {
  method: "POST",
  headers: {
    Authorization: `Bearer ${API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    title: "Checkout fails with 500 on discount code",
    description:
      "Applying SAVE20 at checkout returns HTTP 500. " +
      "Affects all users. Stripe webhook not triggered. " +
      "Steps: 1. Add item to cart, 2. Enter code SAVE20, " +
      "3. Click Apply. Expected: discount applied, order completes. " +
      "Actual: 500 Internal Server Error.",
    severity: "critical",
  }),
});

const report = await response.json();
console.log(`Bug filed: ${report.id} — ${report.type} (${report.severity})`);

🐛

bugAgent auto-classifies the bug type (ui, performance, crash, security, logic, data, network) and assigns a confidence score. You don't need to specify the type — just describe the bug.

What Makes bugAgent Different?

Unlike traditional bug tracking platforms, bugAgent is built from the ground up for AI-native workflows.

bugAgent

AI auto-classifies bugs by type and severity
MCP-native — agents file bugs directly
Natural language input — no forms or templates
Confidence scoring on every classification
API-first with MCP, REST, and CLI
Enrichment pipeline adds context automatically
Zero context-switching for developers using AI
Free tier for agents to get started instantly

Traditional Platforms

Manual classification by humans
GUI-first — agents can't easily interact
Rigid forms with required fields
No intelligence on reports
REST API bolted on as afterthought
Requires manual triage and tagging
Context-switching between IDE and browser
Per-seat pricing, complex onboarding

Next Steps

Ready to dive deeper? Explore these resources:

📖