Integrate Your Agent

Configure your AI agents to automatically report issues when services fail

Quick Start

Get your agent reporting issues in under 5 minutes

Get an API Key

Add to Your Agent

Use our SDK or call the API directly

Report Issues

Your agent automatically reports failures

Your API Keys

Integration Guide

REST API Reference

Direct HTTP API calls for any language or platform

GET
Discovery Endpoint

Agents can discover how to report issues by fetching this well-known endpoint:

GET https://agentup.dev/.well-known/agentup.json

POST
Report an Issue

POST https://agentup.dev/api/agent/report
Content-Type: application/json
Authorization: Bearer YOUR_API_KEY

{
  "service": "openai",
  "type": "timeout",
  "severity": "major",
  "description": "API requests timing out after 30s",
  "metadata": {
    "agent_name": "MyAgent",
    "error_code": "ETIMEDOUT",
    "latency_ms": 30000
  }
}

GET
Check Service Status

GET https://agentup.dev/api/agent/status/openai
Authorization: Bearer YOUR_API_KEY

# Response:
{
  "service": "openai",
  "status": "operational",
  "active_incidents": 0,
  "last_checked": "2024-01-15T10:30:00Z",
  "reports_24h": 5
}

GET
List All Services

GET https://agentup.dev/api/agent/services
Authorization: Bearer YOUR_API_KEY

# Response: Array of all monitored services with current status

Report Types

Use these types when reporting issues

backend_downService is completely unreachable

timeoutRequests taking too long or timing out

rate_limitedGetting rate limit errors

auth_failureAuthentication or API key issues

mcp_failureMCP connection or protocol errors

skill_parse_errorSkill/plugin failed to parse or load

prompt_issueUnexpected responses or prompt failures

otherOther issues not covered above

Setup for Popular Coding Agents

Instructions for integrating AgentUp with the most popular AI coding assistants

Claude Code (Anthropic)

Integrate AgentUp with Claude Code CLI

1. Add to your CLAUDE.md file

Create or edit your project's CLAUDE.md to include AgentUp reporting instructions:

# AgentUp Integration

When you encounter errors with external AI services (OpenAI, Anthropic, MCP servers, etc.), 
report them to AgentUp using this curl command:

```bash
curl -X POST https://agentup.dev/api/agent/report \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AGENTUP_API_KEY" \
  -d '{
    "service": "SERVICE_SLUG",
    "type": "ERROR_TYPE",
    "description": "Error description",
    "severity": "major"
  }'
```

Service slugs: openai, anthropic, mistral, cohere, github-mcp, etc.
Error types: backend_down, timeout, rate_limited, auth_failure, mcp_failure, other

2. Set environment variable

export AGENTUP_API_KEY="your_api_key_here"

3. Add MCP Tool (Optional)

For deeper integration, add AgentUp as an MCP server in your Claude Code config:

{
  "mcpServers": {
    "agentup": {
      "command": "npx",
      "args": ["-y", "@agentup/mcp-server"],
      "env": {
        "AGENTUP_API_KEY": "your_api_key_here"
      }
    }
  }
}

Best Practices

Avoid Duplicate Reports

Implement rate limiting on your side - don't report the same issue more than once per minute. Our API will deduplicate, but it's better to handle client-side.

Include Metadata

Add your agent name, version, and any relevant context to metadata. This helps identify patterns across different agent implementations.

Check Status First

Before making API calls, optionally check if a service is already experiencing issues. This can help you fail fast or use fallbacks.

Secure Your API Key

Store your API key in environment variables, never in code. Rotate keys periodically and revoke any that may have been exposed.