Use AI coding agents with Aspire observability

Give your AI coding agent access to application observability, not just source code. Run aspire agent init in your project to install skills that teach your assistant to use the Aspire CLI, inspect local services, and work with TypeScript or C# AppHosts. A runtime MCP server is optional.

Why Aspire for coding agents

Aspire gives coding agents access to the resource status, health checks, application logs, and distributed traces you inspect in the Aspire dashboard. Start with Aspire skills and the Aspire CLI; add the Aspire MCP server if you want runtime tools exposed through MCP. Both paths let an agent investigate the same request evidence as a developer.

The Aspire CLI is built for agent-driven workflows — commands support non-interactive execution to avoid blocking on prompts, and many commands support --format Json for structured plain text output. Key commands include aspire start (background execution), aspire start --isolated (parallel worktrees), aspire wait (block until healthy), aspire describe, aspire logs, and aspire docs search.

Aspire workflow skills installed by aspire agent init teach agents these patterns automatically.

For skill installation paths, skill locations, companion tools, and the full skill list, see Aspire skills.

Get started

When you create a new Aspire project with aspire new or aspire init, you’re prompted to configure AI agent environments. You can also run aspire agent init at any time to set up or update the configuration.

Open a terminal in your Aspire project directory (the folder containing your AppHost).
Run the following command:
Aspire CLI
```
aspire agent init
```
Select the skill locations, skills and tools, and optional MCP server configuration for the agent environments you use.

For details about skill locations, workflow skills, Playwright CLI, and dotnet-inspect, see Aspire skills.

What gets configured

The aspire agent init command detects your AI development environment and creates the appropriate configuration files:

Aspire skill files

Aspire skill files teach your AI coding agent how to use Aspire CLI workflows, route tasks to focused skills, and call selected companion tools such as Playwright CLI or dotnet-inspect.

For the full skill bundle contents and installation details, see Aspire skills.

Aspire MCP server

The optional MCP server gives your AI agent direct runtime access to your running Aspire application — resource status, logs, traces, and commands. CLI skills can already query runtime data without MCP. See Aspire MCP server for configuration details, available tools, and the security model.

Migrate from AGENTS.md

If your project has an AGENTS.md file from a previous version of Aspire, you can migrate to the new skill file format. Skill files provide better structure and are recognized natively by AI coding agents.

Run aspire agent init and select the Aspire workflow skills you want to install.
The skill files are created under each selected skill location, such as .agents/skills/aspire/SKILL.md and .agents/skills/aspire-orchestration/SKILL.md.
Review and delete the old AGENTS.md file — the skill files replace it.

Your first prompts

Once configured, start your preferred AI coding environment. Try asking your agent:

“Start the Aspire app and show me the resource status.”

“Analyze HTTP request performance for my API.”

“Investigate this failed request using its trace ID and correlated logs. After the fix, repeat the request and verify the response and new trace.”

“Add a Redis cache to my AppHost.”

For a worked investigation using the same evidence in the dashboard and CLI, see Debug application failures with AI coding agents. Passing resource health checks alone doesn’t prove that a failing request is fixed.

Supported AI assistants

The aspire agent init command supports the following AI assistants:

VS Code with GitHub Copilot
Copilot CLI
Claude Code
OpenCode