Skip to content

MCP Tools Reference

The aqua MCP server exposes the following tools. These tools allow AI agents to create, manage, and execute QA plans programmatically.

Tools for creating and managing QA plans and their versions.

ToolDescription
create_qa_planCreate a new QA plan. Auto-detects the current git branch and pull request URL.
get_qa_planRetrieve a plan by ID, including its latest version information.
list_qa_plansList plans with optional status filter and cursor-based pagination.
update_qa_planCreate a new immutable version with the full scenario and step structure. Steps support an optional condition field for conditional execution based on variable values.
update_qa_plan_stepPartial update of a single step. Creates a new plan version. Supports setting a condition for conditional execution.
add_qa_plan_stepAdd a step to a scenario. Creates a new plan version. Supports setting a condition for conditional execution.
remove_qa_plan_stepRemove a step by its key. Creates a new plan version. Fails if other steps depend on it.
set_qa_plan_statusChange the plan status: draft, active, or archived.

Tools for running QA plans and inspecting results.

ToolDescription
execute_qa_planExecute a full plan and record results on the server. Returns a markdown summary and an execution URL. Supports an async parameter for background execution.
run_scenarioExecute a single inline scenario without recording results on the server. Returns detailed debug output.
get_executionFetch execution results including per-step details.
list_executionsList executions filtered by plan ID, version, or status.
get_execution_progressGet the current progress of a running execution. Use this to monitor async executions started with execute_qa_plan(async=true).

Tools for managing environment configurations used during execution.

ToolDescription
create_environmentCreate or overwrite an environment file at .aqua/environments/<name>.json.
list_environmentsList all environment configurations with their notes.
validate_environmentValidate an environment file’s schema and check that secrets can be resolved.

Tools for managing reusable scenario templates that can be copied into QA plans.

ToolDescription
create_common_scenarioCreate a reusable scenario template.
get_common_scenarioRetrieve a common scenario by ID.
list_common_scenariosList all common scenarios in the project.
update_common_scenarioUpdate an existing common scenario.
delete_common_scenarioDelete a common scenario. Does not affect plans that have already copied it.

Tools for capturing browser interactions.

ToolDescription
record_browser_actionsOpen an interactive browser window to record user actions. Returns the recorded actions as a BrowserStep[] array.

Tools for interactively investigating your application one action at a time. Unlike run_scenario, exploration sessions keep the browser alive between calls, allowing you to try selectors, inspect responses, and build up state incrementally. See the Interactive Exploration guide for details.

ToolDescription
start_explorationStart an interactive exploration session. The browser is maintained between actions so you can build up state incrementally.
explore_actionExecute an action within a session (browser step, HTTP request, or browser assertion) and get immediate feedback.
end_explorationEnd an exploration session and clean up resources (browser process, memory).
list_exploration_logsList recent exploration session logs for the current project.
get_exploration_logGet the full action log from a specific exploration session. Can be used to replay successful actions.

Tools for managing persistent project-level knowledge.

ToolDescription
get_project_memoryRetrieve the project memory. Returns a starter template if no memory has been saved yet.
save_project_memorySave project memory. Performs a full overwrite of the existing content.

Tools for checking project readiness.

ToolDescription
check_project_setupOne-shot status check that reports on local config, project memory, environments, and common scenarios.