Testdino MCP connector for AI agents

Tools your QA agent reaches for on TestDino, scoped per user.

CALL ANY TOOL

Test analytics for Playwright: run breakdowns, per-case errors and traces, AI root cause on flaky tests, audit reports, manual suites, releases, and exploratory sessions.

testidinomcp_list_manual_runs

List manual runs

Browse manual test runs for a project. filter by status (active|closed), state (new|in_progress|on_hold|done), environment, release (releaseid), tags, or free-text search on name. default page size 25 (max 200).

Parameters

Name

Type

Required

Description

projectId

string

Required

Project ID (e.g. project_). Obtain from the health tool.

environment

string

Optional

Filter by environment label.

isClosed

boolean

Optional

Filter by closed state (boolean).

limit

integer

Optional

Items per page. Default 25, max 200.

page

integer

Optional

Page number (1-indexed).

releaseId

string

Optional

Filter to runs in this release. Pass "none" to list unlinked runs.

string

Optional

Match by run name.

sortBy

string

Optional

Field to sort results by.

sortOrder

string

Optional

Sort direction.

state

string

Optional

Workflow state. Either canonical ("new", "in_progress", "on_hold", "done") or display ("In Progress", "On Hold") form.

status

string

Optional

Filter by run status: active or closed.

tags

string

Optional

Comma-separated tag names.

testStepsDeclarationType

string

Optional

Step format: "Classic" (action + expectedResult) or "Gherkin" (Given/When/Then).

type

string

Optional

Type. Values come from Project Settings → Test Case Properties. Defaults: Smoke, Regression, Functional, Integration, E2E, API, Unit, Performance, Security, Accessibility, Usability, Compatibility, Acceptance, Exploratory, Other.

testidinomcp_update_manual_test_case

Update manual test case

testidinomcp_list_manual_test_suites

List manual test suites

testidinomcp_get_manual_test_case

Get manual test case

testidinomcp_create_manual_test_suite

Create manual test suite

testidinomcp_update_release

Update release

testidinomcp_list_releases

List releases

testidinomcp_get_release

Get release

testidinomcp_create_release

Create release

testidinomcp_update_run_test_case

Update run test case

testidinomcp_list_run_test_cases

List run test cases

testidinomcp_get_run_details

Get run details

testidinomcp_create_session

Create session

testidinomcp_update_session

Update session

testidinomcp_list_sessions

List sessions

testidinomcp_get_session

Get session

testidinomcp_list_testcase

List testcase

List and filter test cases across runs. requires at least one run context: by_testrun_id, counter, by_pages, by_branch, by_time_interval, by_environment, by_author, or by_commit. when you use by_branch, by_time_interval, by_author, or by_commit, this tool resolves the matching runs internally: you do not need to call list_testruns first. combine filters freely: e.g. by_branch="main" + by_status="failed" + by_time_interval="1d" gives you all failures on main today in one call. batch up to 20 run ids with by_testrun_id="id1,id2,id3". use by_error_category to filter by "timeout_issues", "element_not_found", "assertion_failures", or "network_issues". prefer specific filters over get_all=true.

Parameters

Name

Type

Required

Description

projectId

string

Required

Project ID. Obtain from the health tool.

by_artifacts

boolean

Optional

Filter to test cases that have artifacts.

by_attempt_number

integer

Optional

Filter by attempt number.

by_author

string

Optional

Filter by commit author.

by_branch

string

Optional

Filter by git branch name.

by_browser_name

string

Optional

Filter by browser name, e.g. "webkit", "chromium", "firefox".

by_commit

string

Optional

Filter by commit SHA or message.

by_environment

string

Optional

Filter by environment label.

by_error_category

string

Optional

Filter by error category, e.g. "timeout_issues", "element_not_found", "assertion_failures", "network_issues".

by_error_message

string

Optional

Filter by error message text.

by_pages

integer

Optional

Test-run page (1-indexed, 20 runs per page, newest first). Use to walk back through historical runs when no other run filter is given.

by_spec_file_name

string

Optional

Filter by spec file name.

by_status

string

Optional

Filter by test case status.

by_tag

string

Optional

Comma-separated tag names.

by_testrun_id

string

Optional

Single test run ID or comma-separated (max 20).

by_time_interval

string

Optional

Time filter: "1h", "1d", "weekly", "monthly", "last 5 days", or "YYYY-MM-DD,YYYY-MM-DD".

by_total_runtime

string

Optional

Per-test duration filter. Numbers are milliseconds by default; suffix with `s` for seconds. Examples: ">5000" (>5s), "5s".

counter

string

Optional

Test run counter (alternative to by_testrun_id).

get_all

boolean

Optional

Return all results (max 1000).

limit

integer

Optional

Items per page. Use 0 or -1 for all results (capped at 1000).

offset

integer

Optional

Skip N items (alternative to page).

page

integer

Optional

1-indexed page number (default: 1).

testidinomcp_get_testcase_details

Get testcase details

Get full details of a test case: errors, stack traces, steps, console logs, and artifacts. critical rule: using by_title alone without by_testrun_id or counter returns all executions of that test across every run: this is expensive and usually not what you want. always pair by_title with by_testrun_id or counter to scope to a specific run. use testcaseid for the most precise lookup (no other context needed). always pass steps_filter="failed_only" when debugging: it drops passing setup/hook steps and returns only the erroring step, cutting noise significantly. use include_history=true + history_limit to see pass/fail patterns over time (useful for flakiness analysis). use include_screenshots=true or include_traces=true to get artifact urls for a specific failing execution.

Parameters

Name

Type

Required

Description

projectId

string

Required

Project ID. Obtain from the health tool.

by_code_snippet

string

Optional

Filter by code snippet in the test.

by_error_message

string

Optional

Filter by error message text.

by_fulltitle

string

Optional

Filter by full test case title (including suite prefix).

by_status

string

Optional

Filter by test case status.

by_testrun_id

string

Optional

Filter to a specific test run ID.

by_testrun_ids

string

Optional

Comma-separated test run IDs (max 20).

by_testsuite_id

string

Optional

Filter by test suite ID.

by_title

string

Optional

Filter by test case title. Always pair with by_testrun_id or counter to scope to a specific run.

get_all

boolean

Optional

Return all results (max 1000).

history_limit

integer

Optional

Number of historical executions to include (1-100).

include_artifacts

boolean

Optional

Include artifact URLs in the response.

include_attachments

boolean

Optional

Include attachment URLs in the response.

include_history

boolean

Optional

Include pass/fail history across runs (useful for flakiness analysis).

include_screenshots

boolean

Optional

Include screenshot URLs in the response.

include_traces

boolean

Optional

Include trace URLs in the response.

include_videos

boolean

Optional

Include video URLs in the response.

limit

integer

Optional

Items per page. Use 0 or -1 for all results (capped at 1000).

offset

integer

Optional

Skip N items (alternative to page).

page

integer

Optional

1-indexed page number (default: 1).

sort_by

string

Optional

Sort results by this field.

sort_order

string

Optional

Sort direction.

steps_filter

string

Optional

Use "failed_only" to drop passing setup/hook steps and return only the erroring step.

testcaseid

string

Optional

Exact test case ID(s), comma-separated (max 50).

testidinomcp_list_testruns

List testruns

testidinomcp_debug_testcase

Debug testcase

testidinomcp_health

Health

testidinomcp_submit_audit_report

Submit audit report

Build your Agent

Drop the toolkit in, point it at the user, and your agent can pull run details and debug flaky tests from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["testidinomcp"], toolNames: ["testidinomcp_get_run_details", "testidinomcp_debug_testcase", "testidinomcp_list_manual_runs"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["testidinomcp"], toolNames: ["testidinomcp_get_run_details", "testidinomcp_debug_testcase", "testidinomcp_list_manual_runs"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["testidinomcp"], toolNames: ["testidinomcp_get_run_details", "testidinomcp_debug_testcase", "testidinomcp_list_manual_runs"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/testidinomcp",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start pulling TestDino results into your workflows.

Failure triage

Copy the prompt

Copied

Why is [spec_file] flaky on main this week?

Copy the prompt

Copied

Show the error category breakdown for run [run_id].

Copy the prompt

Copied

List test cases that failed in the last 3 runs but passed before.

Run reporting

Copy the prompt

Copied

Summarize the latest run for project [project_id].

Copy the prompt

Copied

Compare pass rate across the last 10 runs.

Copy the prompt

Copied

Pull the stack trace and console logs for test case [case_id].

Manual QA

Copy the prompt

Copied

Browse manual test runs still in progress for [project_id].

Copy the prompt

Copied

Create a release for v2.4 and link the open runs.

Copy the prompt

Copied

List exploratory sessions closed this sprint with their missions.

SEE HOW AUTH WORKS

Your users connect once. Their Testdino MCP credentials stay vaulted, every call is scope-checked, and every action is logged.

Authorize

Your user connects

Testdino MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Testdino MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Testdino MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Testdino MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other connectors.

ENGINEERING

DevOps assistant agent

Poll GitHub for failing checks and stale pull requests, open Linear issues for the ones that need work, and digest to Slack.

ENGINEERING

Auto-release notes agent

Group merged GitHub PRs into structured release notes, publish the page to Notion, and announce the release in Slack.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
audit → bot_service_account
user_filter → broken

// scalekit
audit → user_abc
scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Testdino MCP today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Testdino MCP as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Testdino MCP OAuth token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Testdino MCP?

Yes. Pass a tool name filter to listScopedTools so the DevOps agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Testdino MCP.

What happens when a user revokes Testdino MCP access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Does the agent get access to every TestDino project?

Only the projects the authorizing user can already open, and only at that user's permission level. Read tools work with read access, while manual-run and release writes need write permission. Scalekit resolves the user's OAuth 2.1 credential per call and logs each one.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit