---
title: "Tools, prompts & commands"
section: "MCP & AI assistants"
description: "Every SmartestQA MCP tool explained in plain words: what it reads or writes and when it asks you. Plus the Status, Modules, Scenarios and Red runs prompts and work keys."
url: https://docs.smartestqa.ai/en/mcp-tools.html
audience: [customer, admin]
updated: 2026-11-08
keywords: "mcp tools smartest_context smartest_status smartest_discover smartest_propose smartest_apply smartest_write_case smartest_run_case smartest_runs smartest_pipeline smartest_heal smartest_defects smartest_integrations smartest_actions smartest_action_write prompts work keys with mcp copy mcp prompt"
---
# MCP & AI assistants: Tools, prompts & commands

You never call these tools yourself: you ask in plain words and the assistant picks them. Knowing them helps you ask well and understand what the assistant reports.

## In short

**On this page you can**

- See which of the 18 tools only read and which can write.
- Start a ready-made prompt: Status , Modules , Scenarios , Red runs .
- Paste a command copied with With MCP or Copy MCP prompt .
- Understand the work keys the assistant reports, such as SCENARIOS or HEAL .

**How to use it**

1. Ask in plain words, naming the project.
2. Let the assistant start with smartest_context or smartest_status .
3. Follow the work key it suggests, riskiest target first.
4. Approve or refuse each change it proposes.

## The 18 tools

Tools that only read run straight away. Tools that write follow the [propose → apply](https://docs.smartestqa.ai/en/mcp-safe-changes.html#propose-apply) rule or ask for a click, as noted.

### Find out where you stand

| Tool | What it does | Writes? |
| --- | --- | --- |
| `smartest_context` “Where are we” | The first call. Without a project, lists your projects so the assistant can ask which one. With a project: where it stands, what a [module](https://docs.smartestqa.ai/en/analyze-folders.html#modules), [requirement](https://docs.smartestqa.ai/en/analyze-requirements.html) or [scenario](https://docs.smartestqa.ai/en/automate-test-cases.html#create-test-case) holds, what comes next, and the rules for that level. With a [work key](https://docs.smartestqa.ai/en/mcp-tools.html#work-keys): its targets, riskiest first. | No |
| `smartest_status` | The status of the project or a module: the [Test Health](https://docs.smartestqa.ai/en/insight-test-health.html) numbers ([coverage](https://docs.smartestqa.ai/en/insight-test-health.html#pillars), [funnel](https://docs.smartestqa.ai/en/insight-test-health.html#funnels)), the [sub-requirements](https://docs.smartestqa.ai/en/analyze-requirements.html#sub-requirements) automation cannot prove, and the open work as work keys with counts, in priority order. | No |
| `smartest_discover` “Discover what is known” | What SmartestQA already knows when there is no code, browser or document to read: [pages](https://docs.smartestqa.ai/en/discover-app-map.html) with their actions, the saved [API library](https://docs.smartestqa.ai/en/api-requests-library.html), [documents](https://docs.smartestqa.ai/en/analyze-folders.html#documents), the [browser and device commands](https://docs.smartestqa.ai/en/automate-steps-code.html#commands) a script step may use, and [what uses a data key](https://docs.smartestqa.ai/en/data-source-variables.html#connected-actions). | No |
| `smartest_actions` “Action catalog” | The [actions](https://docs.smartestqa.ai/en/discover-actions.html#action-list) (controls) element steps use, with their locators and how many scenarios use each; by page or module. | No |
| `smartest_case_rules` | The rules for writing scenario steps, by topic ([web](https://docs.smartestqa.ai/en/automate-steps-browser.html), [mobile](https://docs.smartestqa.ai/en/automate-steps-mobile.html), [desktop](https://docs.smartestqa.ai/en/automate-steps-desktop.html), [API](https://docs.smartestqa.ai/en/automate-steps-api.html), [database](https://docs.smartestqa.ai/en/automate-steps-database.html), [mail](https://docs.smartestqa.ai/en/automate-steps-mail.html), [AI steps](https://docs.smartestqa.ai/en/automate-steps-ai.html), [templates](https://docs.smartestqa.ai/en/automate-steps-flow.html#template)…), with a rules version the writer checks. | No |

### Change records

| Tool | What it does | Writes? |
| --- | --- | --- |
| `smartest_propose` “Propose a change” | Turns a draft into a diff with its impact, hints and a preview id. Levels: environment, [module](https://docs.smartestqa.ai/en/analyze-folders.html#modules), [main requirement](https://docs.smartestqa.ai/en/analyze-requirements.html#create-main), [sub-requirement](https://docs.smartestqa.ai/en/analyze-requirements.html#sub-requirements), [note](https://docs.smartestqa.ai/en/discover-notes.html), [document](https://docs.smartestqa.ai/en/analyze-folders.html#documents), [page (purpose, roles)](https://docs.smartestqa.ai/en/discover-app-map.html#page-information), scenario plan, [data keys](https://docs.smartestqa.ai/en/data-source-variables.html#create-key), [actions](https://docs.smartestqa.ai/en/discover-actions.html), [defect](https://docs.smartestqa.ai/en/tasks.html), [load test](https://docs.smartestqa.ai/en/automate-steps-load.html), API inventory. Intents: create, enrich (only adds), update, reorganize, remove. | No: it writes nothing |
| `smartest_apply` | Writes exactly what the preview showed, after you approved it. | Yes, after your yes; removals need an [Admin](https://docs.smartestqa.ai/en/company-settings-roles.html#matrix) and [a click](https://docs.smartestqa.ai/en/mcp-safe-changes.html#confirmations) |
| `smartest_action_write` | Creates actions or changes an action’s locators, name or page. First call shows the diff and the scenarios each change touches; the second call, with only the preview, writes it. | Yes, after your yes |
| `smartest_api_library` | Adds or changes a request in the [API library](https://docs.smartestqa.ai/en/api-requests-library.html). Tokens and passwords are [data source references](https://docs.smartestqa.ai/en/data-source-in-tests.html#reference-syntax), never plain values. | Yes |

### Write and run scenarios

| Tool | What it does | Writes? |
| --- | --- | --- |
| `smartest_write_case` | Writes the steps of a planned scenario and [dry-runs it](https://docs.smartestqa.ai/en/automate-dry-run.html#start-dry-run) on the server or on your [online agent](https://docs.smartestqa.ai/en/agent-pool-agents.html#agent-status). All [quality checks](https://docs.smartestqa.ai/en/mcp-safe-changes.html#guards) run before anything is written. If the run is red, it names the failed step and its cause; the third red run marks the scenario [**BLOCKED**](https://docs.smartestqa.ai/en/mcp-safe-changes.html#scenario-flow). | Yes (the scenario you approved in its plan) |
| `smartest_run_case` | Dry-runs a written scenario again, steps unchanged, after you fixed a [locator](https://docs.smartestqa.ai/en/discover-actions.html#inline-edit), [data](https://docs.smartestqa.ai/en/data-source-variables.html) or the [environment](https://docs.smartestqa.ai/en/automate-editor.html#environment). | Starts a run |
| `smartest_run_status` | The result of a dry run that was still running when the assistant stopped waiting. | No |

### Pipelines

| Tool | What it does | Writes? |
| --- | --- | --- |
| `smartest_module_pipelines` | Builds and fills a module’s standard [pipelines](https://docs.smartestqa.ai/en/schedule-create.html) (functional, API, security) and adds its scenarios to the project’s Smoke, E2E and Known defects pipelines, by [their tags](https://docs.smartestqa.ai/en/schedule-create.html#tags). | Yes |
| `smartest_pipeline` | Lists pipelines, [runs one](https://docs.smartestqa.ai/en/schedule-runs.html#run-now), reads a run’s outcome (waiting up to 50 seconds), and [sets a schedule](https://docs.smartestqa.ai/en/schedule-timing.html#set-schedule) for a pipeline that has passed once. It asks you the time and [time zone](https://docs.smartestqa.ai/en/schedule-timing.html#time-zone). | Run and schedule: yes |

### Results, maintenance and defects

| Tool | What it does | Writes? |
| --- | --- | --- |
| `smartest_runs` “Runs, reports and logs” | [Reports](https://docs.smartestqa.ai/en/report-list.html) newest first, one run per scenario, a scenario run [step by step](https://docs.smartestqa.ai/en/report-steps.html#step-table) with its failed step, locators and screenshot, pass/fail history, what runs now and runner health. It can [stop a run](https://docs.smartestqa.ai/en/report-list.html#stop-a-run), cancel a self-hosted runner job that has not started yet, and [mail a report](https://docs.smartestqa.ai/en/report-summary.html#share-report). It cannot stop a [dry run](https://docs.smartestqa.ai/en/automate-dry-run.html#close-panel): no one can. | Stop, cancel and mail ask for a click |
| `smartest_heal` “Auto-heal decisions” | Healed locators waiting for a decision (the same list as in [**Maintain**](https://docs.smartestqa.ai/en/maintenance-auto-heal.html#the-screen)). [Approve or reject](https://docs.smartestqa.ai/en/maintenance-auto-heal.html#review-a-repair) one record: first a preview, then again after you agree. Reject restores the locators from before the heal. | Yes, after your yes |
| `smartest_defects` “Tasks and defects” | Open [defects](https://docs.smartestqa.ai/en/tasks.html), one in full, the company’s [status names](https://docs.smartestqa.ai/en/company-settings-task-settings.html), [comments](https://docs.smartestqa.ai/en/tasks-detail.html#comments) and [attachments](https://docs.smartestqa.ai/en/tasks-detail.html#attachments); update, close (with what was done), comment, attach. A new defect is proposed with `smartest_propose`. Defects cannot be deleted, only closed. | Update, close, comment, attach |
| `smartest_integrations` | Systems set up in SmartestQA: [Jira](https://docs.smartestqa.ai/en/integrations-issue-trackers.html#jira), [Xray](https://docs.smartestqa.ai/en/integrations-test-management.html#xray) and [Confluence](https://docs.smartestqa.ai/en/integrations-confluence.html) (find, map, sync, comment, export), the [test mailbox](https://docs.smartestqa.ai/en/integrations-email.html) (messages, wait, one-time codes, links), [databases and Kafka](https://docs.smartestqa.ai/en/data-source-connections.html) (list, query, execute) and [Excel sources](https://docs.smartestqa.ai/en/data-source-datasets.html). | Bulk sync and database execute ask for a click |

## Ready-made prompts

MCP clients that show prompts (Claude Desktop: the **+** menu of the chat) offer four. Each asks for the project id (and optionally a module id); leave it empty and the assistant asks which project.

| Prompt | Does |
| --- | --- |
| **Status** | Where the project or a module stands: the numbers and what comes first. |
| **Modules** | Groups the [recorded pages](https://docs.smartestqa.ai/en/discover-app-map.html) into [modules](https://docs.smartestqa.ai/en/discover-app-map.html#modules) by business area. |
| **Scenarios** | Plans and writes scenarios for the [sub-requirements](https://docs.smartestqa.ai/en/analyze-requirements.html#sub-requirements) that have none, riskiest first. |
| **Red runs** | Reads the red [pipeline runs](https://docs.smartestqa.ai/en/schedule-runs.html#history), [classifies them](https://docs.smartestqa.ai/en/report-ai-analysis.html#verdicts), fixes them or proposes [defects](https://docs.smartestqa.ai/en/tasks.html). |

## Commands from the app

Several buttons copy a ready request to your clipboard:

- **With MCP** on the [Setup Roadmap](https://docs.smartestqa.ai/en/discover.html#screen-tour): “Command copied. Paste it into Claude (or another assistant connected to the SmartestQA MCP).” [**MCP setup**](https://docs.smartestqa.ai/en/mcp-connect.html#claude-desktop) opens the [MCP tab in Test Agents](https://docs.smartestqa.ai/en/agent-pool-agents.html#mcp-tab).
- [**Copy MCP prompt**](https://docs.smartestqa.ai/en/insight-test-health.html#fix-these-first) in [Test Health](https://docs.smartestqa.ai/en/insight-test-health.html): “Copies a ready prompt. Paste it into Claude or any MCP client and it does the work.”

The first line of such a request is a command the assistant recognises:

Command line format

```text
SmartestQA project 12 · SCENARIOS
SmartestQA project 12 · HEAL · module:4
```

It means: in project 12, work on the key `SCENARIOS` (optionally for module 4). The assistant calls `smartest_context` with that key and starts with the riskiest target.

## Work keys

The assistant names open work with these keys, in `smartest_status` and in commands.

| Key | Means |
| --- | --- |
| `ENV` | The environment is not complete (language, [start URL](https://docs.smartestqa.ai/en/project-settings-project.html#start-pages), [where runs happen](https://docs.smartestqa.ai/en/schedule-where.html)) |
| `MODULES` | Recorded pages that belong to no [module](https://docs.smartestqa.ai/en/discover-app-map.html#modules) |
| `REQUIREMENTS` | [Main requirements](https://docs.smartestqa.ai/en/analyze-requirements.html#create-main) in no module, modules without a main requirement |
| `SUBS` | Main requirements without a [sub-requirement](https://docs.smartestqa.ai/en/analyze-requirements.html#sub-requirements) |
| `SCENARIOS` | Sub-requirements without a scenario |
| `PROVE` | [Risky sub-requirements](https://docs.smartestqa.ai/en/insight-test-health.html#pillars) that are not proven |
| `ASSERT` | Scenarios that [check](https://docs.smartestqa.ai/en/automate-steps-assertions.html) no result |
| `API` | The module’s API inventory, endpoints without an [API scenario](https://docs.smartestqa.ai/en/automate-steps-api.html), writes without a refusal scenario |
| `SECURITY` | Critical endpoints without their security checks |
| `CLEANUP` | Scenarios that create data and remove nothing |
| `HEAL` | Red [pipelines](https://docs.smartestqa.ai/en/schedule-runs.html#history) |
| `DEFECTS` | Open [defects](https://docs.smartestqa.ai/en/tasks.html) (the assistant offers to close those whose scenario ran green) |
| `DATA` | [Data keys](https://docs.smartestqa.ai/en/data-source-variables.html#create-key) without a value, scenarios that refer to a missing key |
| `PIPELINES` | Green scenarios in no [pipeline](https://docs.smartestqa.ai/en/schedule-create.html#add-content), pipelines that never ran or have no [schedule](https://docs.smartestqa.ai/en/schedule-timing.html) |
| `SMOKE` | A module whose main path is not in Smoke |
| `GREEN` | Ready scenarios that never passed in a pipeline run |
| `CURATE` | Scenarios [linked](https://docs.smartestqa.ai/en/analyze-test-cases.html#link-existing) to no requirement |
| `PERF` | Critical endpoints without a [load test](https://docs.smartestqa.ai/en/automate-steps-load.html) |
| `AGENTS` | No [autonomous agent](https://docs.smartestqa.ai/en/ai-agents.html) watches the project |
| `STATUS` | The status report |

## How to read the assistant’s answers

- Every tool answers **ok**, **fail** or **ask**. A text that starts with “X” is a failure: the assistant must say what failed and must not report it as done.
- **ASK USER** means the assistant has to ask you before going on, for example to approve a diff or to choose a project.
- **NEXT:** names the call that usually comes next. The assistant follows SmartestQA’s hints before its own ideas, and can go against a [quality gate](https://docs.smartestqa.ai/en/mcp-safe-changes.html#guards) only by naming it and giving a reason.
- Tool results are in English. The assistant restates what matters in your language.
