DEV Community

Cover image for Apidog AI Agent Debugger: Availability, Coverage, and Setup
Hassann
Hassann

Posted on • Originally published at apidog.com

Apidog AI Agent Debugger: Availability, Coverage, and Setup

Apidog’s AI Agent Debugger is available in the latest Apidog client across all plans, including Free. You can use it to run AI agents against OpenAI and Anthropic models, connect MCP servers, inspect every model call and tool invocation in a Traces panel, and track per-run cost.

Try Apidog today

This guide shows who can use the AI Agent Debugger, what it supports, what it does not support, how to enable it, and what stays unchanged in your existing Apidog projects.

What’s available

The AI Agent Debugger ships in the standard Apidog client. There is no separate license, add-on plan, or per-seat fee.

  • Free, Basic, Professional, and Enterprise plans all include the AI Agent Debugger.
  • The feature is enabled by default.
  • You must use the latest Apidog client version. Older clients do not include the AI Agent Debugger tab.

Supported model providers

Provider Status Models
OpenAI Supported GPT-5.5, GPT-5.5 Instant, o-series, and any model on the OpenAI account
Anthropic Supported Claude 4.7 Sonnet, Claude 4.7 Opus, Claude 4.7 Haiku
Custom OpenAI-compatible endpoints Supported via Base URL override Any provider exposing an OpenAI-compatible API
Other providers, including Google, Mistral, and xAI On the roadmap Not currently first-class

MCP server connection methods

The debugger supports the Model Context Protocol natively. You can connect MCP servers with three transports:

  • STDIO: Runs a local subprocess. Use this for MCP servers under active development.
  • HTTP Streamable: Connects to hosted MCP servers over HTTP.
  • SSE: Uses legacy Server-Sent Events. This is still supported for backward compatibility.

MCP server authentication supports:

  • Standard headers, such as API keys.
  • OAuth 2.0 with full token exchange.

What the debugger captures

The debugger records the full execution chain for an agent run, including:

  • Model calls with full request and response payloads.
  • Model thinking traces when the model exposes them, such as OpenAI o-series or Anthropic extended thinking.
  • Tool invocations with parameter values and return data.
  • MCP server traffic, shown in the Traces panel like any other tool call.
  • Built-in tools:
    • bash
    • web_fetch
    • read
    • edit
    • write
    • grep
    • glob
    • kill_shell
  • Per-run performance metrics:
    • Response time
    • Input tokens
    • Output tokens
    • Estimated cost
  • Skills, which are saved bundles of system prompt, tool list, and parameters for rerunning a scenario.

What the debugger does not cover

The AI Agent Debugger is designed for local agent debugging, not every agent workflow. It does not cover:

  • Production observability: Use a dedicated observability tool for long-term traffic logging.
  • Automated regression testing: For grids of prompts against fixtures, use a harness like Promptfoo.
  • Agent-to-Agent protocol traffic: For A2A traffic, use Apidog’s separate A2A Debugger.
  • MCP server validation in isolation: To test a single MCP server’s tools and resources without an agent loop, use Apidog’s MCP server testing flow.

How to enable it

  1. Update Apidog to the latest version.
  2. Open Apidog.
  3. Click AI Agent Debugger in the top tab bar.
  4. Select a model provider and model.
  5. Confirm the Base URL. It auto-populates from the selected provider.
  6. Override the Base URL if you are using a custom OpenAI-compatible endpoint.
  7. Paste your API key.
  8. Click Run on an empty thread to confirm the connection.

No project-level configuration is required. The debugger runs in its own workspace.

What stays the same

Using the AI Agent Debugger does not change your existing Apidog setup.

  • Existing Apidog projects, API definitions, and test suites are unaffected.
  • The MCP server testing flow and the A2A Debugger continue to work in parallel.
  • API endpoint debugging, mock servers, and OpenAPI editing are unchanged.
  • Billing and plan tiers are unchanged.
  • The AI Agent Debugger does not consume any new Apidog credit.

You still pay for the underlying model API calls based on your OpenAI or Anthropic account billing. Apidog does not surcharge for usage.

For Team and Enterprise admins

For team environments, use the following model:

  • The AI Agent Debugger is enabled per user.
  • Each member uses their own provider API key.
  • API keys entered in the debugger are stored locally on each user’s client.
  • API keys are not transmitted to Apidog servers.
  • Workspace owners can centrally manage shared MCP server endpoints through standard Apidog environment variables.
  • Audit and access controls for MCP servers follow the MCP server’s own authentication model, such as headers or OAuth 2.0.

Known limitations

Before using the debugger in a team workflow, note these current limitations:

  • Provider expansion beyond OpenAI and Anthropic is on the roadmap.
  • For OpenAI-compatible providers, use the Base URL override.
  • Trace sharing is local only.
  • To share a trace, copy the Raw view JSON or screenshot the panel.
  • Cost estimation is a local approximation based on published model pricing.
  • For billing, refer to your provider’s usage dashboard.

Top comments (0)