MCP tools for AI coding agents

Shows which step a PDLC session has reached.

Try: “Where did we get to with the password reset feature?”

Lists the PDLC sessions in the connected workspace, most recently updated first, up to 50.

Try: “What work sessions do I have open in Test Maze?”

Lists the test cases in the connected workspace, 20 per page, sorted by caseId.

Try: “What test cases do we already have for login?”

Reads one test case in full: title, description, pre-condition, steps (in order), expected result, post-condition, priority, status, acceptance-criterion label, waiver details (isWaived, waivedReason, waivedBy, waivedAt), severity, automationStatus, the store…

Try: “Show me the steps of the checkout test”

Creates one test case in the connected workspace: a written check of the app with steps to follow and the result to expect, for example "Guest can check out without an account".

Try: “Write a test case for signing up with an email address”

Changes an existing test case, for example to fill in the steps and expected result of a draft, or to archive it with status INACTIVE.

Try: “Fill in the missing steps for the checkout test”

Creates up to 200 test cases in one call and can file them all under a feature or user story.

Try: “Write test cases for every acceptance criterion of the checkout feature”

Marks an acceptance-criterion test case as waived: a deliberate, recorded decision that this promise does not have to be proven for now (for example "Apple Pay is out of scope for the beta").

Try: “We are skipping the Apple Pay criterion for the beta, mark it as waived”

Permanently deletes one test case.

Try: “Delete that duplicate login test you just made”

Permanently deletes up to 200 test cases in one call.

Try: “Clean up all the duplicate test cases you created”

Undoes case.waive_ac: the acceptance criterion (a testable promise the feature makes) must be proven again.

Try: “Apple Pay is back in scope, remove the waiver”

Lists the test runs in the connected workspace, newest first, 20 per page, optionally filtered by name.

Try: “Did the last test run pass?”

Reads the summary of one test run in the connected workspace: { id, uri, name, buildVersion, description, startDate, endDate, status, gitSha, branch, workingTreeClean, releaseId, frozen, numberOfTestCases }.

Try: “How many tests were in yesterday's run?”

Saves the outcome of each test case onto a test run that already exists: Pass, Fail or Not Executed, plus optional details (what actually happened, the error text, a note, a screenshot).

Try: “I ran the checkout tests: 4 passed, the coupon one failed. Record that”

Creates a test run: one execution of a chosen set of test cases, where each case gets a result (Pass, Fail or Not Executed).

Try: “Run the checkout tests against my current commit and tell me if it is ready to ship”

Tells you which Test Maze workspace this connection reads from and writes to, which user your changes are credited to, and which access token was used.

Try: “Which Test Maze workspace am I connected to?”

Reads the product description stored on the connected workspace.

Try: “What does Test Maze know about my app so far?”

Edits the product description stored on the connected workspace (the "product" is the workspace itself).

Try: “Save this product vision and target audience to Test Maze”

Lists the features, sub-features, user stories and regression suites in the connected workspace.

Try: “What features do we already have in Test Maze?”

Creates a feature: a named capability of the product, such as "Checkout" or "Password reset".

Try: “Add a feature for guest checkout”

Creates a user story: one specific thing a user needs from a feature, written in three parts.

Try: “Write a user story for paying with a saved card”

Records where a feature, sub-feature or user story is in its life.

Try: “Checkout is built, mark it as being verified”

Links a feature (or user story) to the release, sprint or milestone it is planned to ship in, or removes that link.

Try: “Put guest checkout into the June release”

Lists the test plans in the connected workspace, 20 per page, optionally filtered by name.

Try: “Do we already have a smoke test plan?”

Creates a test plan: a named, reusable bundle of existing test cases you want to run together (for example a "Checkout smoke" plan with the five most important checkout cases).

Try: “Group the login and checkout tests into a smoke test plan”

Lists the releases, sprints and milestones in the connected workspace, newest first.

Try: “What releases do we have planned?”

Creates a time-boxed bucket to plan work into.

Try: “Create a v2.0 release targeting the end of June”

Records that a release, sprint or milestone is done and out: sets status to "shipped" and stamps shippedAt with the current time.

Try: “We just shipped v2.0, record it”

Marks a release, sprint or milestone as cancelled, for when the plan is dropped and it will not ship.

Try: “Cancel the v2.1 release, we are not doing it”

Lists the product KPIs in the connected workspace, newest first.

Try: “What KPIs are we tracking for the product?”

Lists the success metrics attached to features in the connected workspace, newest first.

Try: “How are we measuring whether checkout is working?”

Defines a new product KPI (key performance indicator): one number that shows whether the whole product is succeeding.

Try: “Track weekly active users with a goal of 5,000”

Defines how you will tell whether one feature is working for users.

Try: “How will we know guest checkout worked? Track conversion rate from 42% to 55%”

Records one measured value for a product KPI or a feature metric at a point in time, building up its history.

Try: “Log 4,200 weekly active users for this week”

Lists files stored in the connected workspace, such as screenshots taken during test runs, newest first.

Try: “Show me the screenshots from the last test run”

Uploads a file you already have, such as a screenshot of a bug, a short screen recording or a spec document, and optionally attaches it to a test case, test run or feature.

Try: “Attach this screenshot of the broken checkout page to the checkout test”

Step 1 of the Test Maze loop: project.initialize → feature.implement → feature.verify → testrun.create (or testrun.record_results) → pdlc.verify.

Try: “Set up Test Maze for this project”

Step 2 of the loop (project.initialize → feature.implement → feature.verify → testrun.create → pdlc.verify).

Try: “Let's build a password reset flow, plan it and write the tests first”

Step 3 of the loop (project.initialize → feature.implement → feature.verify → testrun.create → pdlc.verify).

Try: “Write the full test steps for the password reset stories”

Final step of the loop (project.initialize → feature.implement → feature.verify → testrun.create / testrun.record_results → pdlc.verify).

Try: “Did the last test run pass? What should I fix first?”

Checks which kinds of testing a feature or user story has no test cases for yet.

Try: “What kinds of tests is the checkout feature missing?”

Freezes a test run as a regression baseline: a set of tests that must keep passing from now on.

Try: “Everything passes now, lock this in so we notice if it breaks later”

Unfreezes a test run so its cases no longer have to keep passing.

Try: “We removed the old checkout, stop requiring its tests to pass”

Lists every frozen test run (regression baseline) in the connected workspace, most recently frozen first.

Try: “Which tests are locked in as must-stay-green?”

Saves the message the user just typed to you onto the Agent Sessions page in Test Maze.

Try: “Keep a log of what I ask you in Test Maze”

Starts an exploration session: a recorded walk through a running web app to discover its pages, links and forms, which can later become test cases.

Try: “Explore my app at http://localhost:3000 and find all the pages”

The core of the exploration loop.

Try: “Keep exploring the app and tell me what pages you find”

Closes an exploration session so no more observations can be added.

Try: “That's enough exploring, wrap it up”

Turns what an exploration session recorded into draft test cases.

Try: “Turn that exploration into test cases”

Lists recent exploration sessions in the connected workspace, from every user, most recently updated first.

Try: “What explorations have we run so far?”

Reads one exploration session from the connected workspace in full.

Try: “Show me everything the last exploration found”

Scans a file, function or diff for code smells: warning signs that code will be hard to change, such as a very long function, a function with many parameters, or the same block copy-pasted.

Try: “Check the file I just wrote for code smells”

Suggests ways to structure code for a design problem you describe in plain words, such as "three payment providers with different APIs", "undo for editor actions" or "one class that changes for every feature".

Try: “How should I structure support for Stripe, PayPal and Razorpay without a giant if/else?”

Searches the built-in code-quality guide (a knowledge base of design patterns, code smells and refactorings) by a symptom you notice or by a name, e.g.

Try: “What is it called when a function takes way too many arguments?”

Reads one entry of the code-quality guide in full: a design pattern, a code smell or a refactoring, with what it is, when to use it, how it looks, an example, trade-offs and step-by-step mechanics.

Try: “Explain the strategy pattern with an example”