AI Assistants and MCP

Autonomy publishes a hosted Model Context Protocol server so AI assistants can run QA from the editor without becoming the browser or device driver. A connected client can find existing plans, generate missing coverage, trigger runs against preview targets, inspect failures, and pull trace context straight into the coding workflow.

https://app.autonomyqa.com/api/mcp

How it connects

• Transport — one remote server over Streamable HTTP. There is no local install or stdio process to manage.
• Authorization — OAuth 2.0 in the browser. The first time a client connects, Autonomy opens a sign-in window where you pick the organization that owns your plans and runs. There is no static API key to paste.
• Scope — access is limited to the signed-in user and the selected organization.

What an assistant can do

A connected client works with plans, runs, traces, environments, and evidence links. It can trigger web, API, iOS, and Android runs using a saved environment or explicit targets from CI and preview systems. It does not expose raw browser clicks, native device automation, or arbitrary network execution. See Available Actions for the full list.

Use MCP when an assistant should check whether a flow already has evidence, run a smoke plan after a change, or inspect a failed run before proposing a fix. The useful pattern is one coding agent changing the product and an Autonomy-backed QA loop validating it with evidence.

Where MCP fits

• Dashboard — humans review plans, runs, settings, and evidence.
• GitHub — pull requests receive run status and evidence links.
• MCP — AI assistants inspect coverage, trigger QA, and diagnose failures from their editor or agent runtime.

Get started

1. Connect a client with the server URL above.
2. Authorize an organization in the browser.
3. Run the First MCP Run workflow against a preview URL, API base URL, or saved environment.
4. Use Available Actions as the reference for tool names and trigger target fields.