Query Log

The Developer FAQs

What model does the execution use?

The model depends on your local LLM client, but this is tested and works best with Claude Sonnet & Opus.

Will Opsera read my code?

No, the code never leaves your local environment. The local LLM performs the code scans, and only metadata like file names, directory structure, language, and frameworks are sent to Opsera for agent orchestration.

How does the MCP integration work?

Opsera agents communicate through the Model Context Protocol (MCP). You configure your IDE (Claude Code, Cursor, or VS Code) with the Opsera MCP server URL, and the agents become available as tools within your existing workflow.

Is my data secure?

Absolutely. Code analysis happens locally through your LLM client. Only anonymized metadata and agent results flow through our servers. All communication is encrypted with TLS, and we follow SOC2 compliance practices.

Can I use multiple agents at once?

Yes! You can invoke different agents sequentially within the same conversation. For example, run Architecture Analyze first, then follow up with Security Scan — all in the same IDE session.

What IDEs are supported?

Currently, Opsera agents work with Claude Code (CLI), Cursor, and VS Code through MCP integration. We’re actively working on expanding IDE support.

How do I get started?

Sign up for a free account, configure the MCP server URL in your IDE, and start using agents immediately. Check the Configuration tab for step-by-step setup instructions.

What happens after the free trial?

During the free trial, you get full access to all agents and features. We’re building flexible pricing tiers — you’ll be notified before any changes to your access.