all tools / testing
As of the latest check, Glimind tracks 146 testing AI agent (MCP) tools, of which 16 are healthy right now. The table below ranks them live-first by real-time reliability.
| tool | status | what it does | |
|---|---|---|---|
| assay_provider_protocol com.alphaassay/mcp | healthy | Use this when you want to judge ANY signal seller -- including us -- with a machine-readable seven-test falsification protocol you can run i | alternatives |
| getScreenshotTestResult io.github.LambdaTest/mcp | healthy | Retrieve the results and screenshot URLs for a completed or in-progress screenshot test. | alternatives |
| stopScreenshotTest io.github.LambdaTest/mcp | healthy | Stop an active screenshot test before it completes. | alternatives |
| getAnalyticsErrors io.github.LambdaTest/mcp | healthy | Summarises failed and errored automation tests in a date range: counts by failure category and by status, and the failing tests themselves w | alternatives |
| getMobileCapabilityGenerator io.github.LambdaTest/mcp | healthy | Retrieve capability generation data for mobile automation test configuration. | alternatives |
| getMobileConcurrency io.github.LambdaTest/mcp | healthy | Retrieve the current concurrency usage and limits for mobile automation (real device testing). | alternatives |
| getFlakyTests io.github.LambdaTest/mcp | healthy | Lists tests that the insights engine marks as flaky (passing and failing intermittently) in a date range, with each test's flake rate, build | alternatives |
| listDevicesForTesting io.github.LambdaTest/mcp | healthy | Retrieve all available real devices on LambdaTest for mobile app testing. Filter by region and OS. | alternatives |
| listMobileBuilds io.github.LambdaTest/mcp | healthy | Retrieve all mobile automation builds from the LambdaTest mobile automation API. | alternatives |
| getPerformanceTestResult io.github.LambdaTest/mcp | healthy | Retrieve the results of a completed performance test including Core Web Vitals, load times, and performance scores. | alternatives |
| listUploadedApps io.github.LambdaTest/mcp | healthy | Retrieve all apps uploaded to LambdaTest for mobile testing. Use type=android/ios for real devices, emulator/simulator for virtual devices. | alternatives |
| deleteUploadedApps io.github.LambdaTest/mcp | healthy | Delete one or more uploaded apps from LambdaTest by their app IDs. | alternatives |
| uploadAppVirtualDevice io.github.LambdaTest/mcp | healthy | Upload an app (APK for emulator, IPA for simulator) to LambdaTest for virtual device (emulator/simulator) testing. | alternatives |
| checkAppProcessingStatus io.github.LambdaTest/mcp | healthy | Check whether an uploaded app has been processed and is ready for features like image injection, network logs, and screenshot unblock on rea | alternatives |
| getTestTrends io.github.LambdaTest/mcp | healthy | Daily trend of automation test results in a date range: for each day, total tests, passed, failed, completed without a pass/fail mark, pass | alternatives |
| test_signal io.github.valuein/mcp-sec-edgar | healthy | Fire a synthetic notification through EVERY channel the signal is configured with. Use this immediately after `create_signal` to verify the | alternatives |
| deleteSmartMock io.github.keploy/mcp | auth | DELETE /apps/{appId}/smart-set/mocks/{name} — Delete a smart-set mock (branch-only) — Tombstone a smart-set mock on a branch. `branch_id` is | alternatives |
| delete_mock io.github.keploy/mcp | auth | Drop one mock from a test set. Idempotent — returns 200 even if the mock is already gone, so retries on a network blip are safe. Accepts UU | alternatives |
| deleteMock io.github.keploy/mcp | auth | DELETE /apps/{appId}/recordings/{testSetId}/mocks/{mockId} — Drop one mock — Idempotent — returns 200 even if the mock is already gone. Path | alternatives |
| create_test com.maxoperf/maxoperf | auth | Create a test shell (choose the engine/executor) | alternatives |
| createTestSuite io.github.keploy/mcp | auth | POST /apps/{appId}/test-suites — Create a test suite — Requires scope: `write`. | alternatives |
| deleteTestSuite io.github.keploy/mcp | auth | DELETE /apps/{appId}/test-suites/{suiteId} — Delete a test suite — Requires scope: `write`. | alternatives |
| create_mock io.github.keploy/mcp | auth | Author a single mock inside a test set. Use this when the dev wants to add a hand-written downstream-call recording (HTTP response, DB resul | alternatives |
| delete_recording io.github.keploy/mcp | auth | Wholesale-delete a recording (test set + its cases + mocks + mapping). `branch_id` is REQUIRED — the delete lays a tombstone overlay on the | alternatives |
| deleteSmartTestCase io.github.keploy/mcp | auth | DELETE /apps/{appId}/smart-set/cases/{name} — Delete a smart test case (branch-only) — Delete a smart case on a branch — a tombstone overlay | alternatives |
| get_test_overview com.maxoperf/maxoperf | auth | Run-history overview for a test | alternatives |
| get_test com.maxoperf/maxoperf | auth | Get one test + its validation summary | alternatives |
| list_tests com.maxoperf/maxoperf | auth | List tests (filter by project / workspace / type) | alternatives |
| get_test_fixture ai.primateintelligence/mcp | auth | Stable fixture for integration self-verification | alternatives |
| get_trace_summary io.github.vola-trebla/playwright-trace-decoder-mcp | unknown | Returns failing action, top-level error, total action count | alternatives |
| baseline realdone | unknown | Creates a baseline of current behavior for regression testing. | alternatives |
| run_playtest kevinnie2003/playtest-agent | unknown | Run a playtest session and generate a bug report | alternatives |
| update_test_execution zephyr-scale-mcp-server | unknown | Update a test case execution's overall status within a cycle, set per-step results, add a comment, and attach bugs as Jira issue links. (Clo | alternatives |
| get_test_cycles_for_issue zephyr-scale-mcp-server | unknown | Get the Zephyr test cycles linked to a Jira issue (story/epic). (Cloud only) | alternatives |
| safe_test_campaign listmonk-mcp-bridge | unknown | Safely test a campaign | alternatives |
| clear_expectations com.mock-server/mockserver | unknown | Clear expectations and/or recorded requests from MockServer | alternatives |
| retrieve_expectations com.mock-server/mockserver | unknown | Retrieve the list of current expectations from MockServer | alternatives |
| retrieve_recorded_requests com.mock-server/mockserver | unknown | Retrieve recorded requests that match the given criteria | alternatives |
| verify io.github.Ideelab/uisandbox | unknown | Runs a 1:1 check in headless Chromium comparing untouched vs tokenised computed styles per element, plus reach. | alternatives |
| run_filtered test-warden | unknown | Rerun tests matching a filter. | alternatives |
| arachne_visual_gates Samuelfmedeiros/Arachne MCP Server | unknown | Deterministic audit: overflow, text collision, JS errors | alternatives |
| arachne_visual_report Samuelfmedeiros/Arachne MCP Server | unknown | Test suite → HTML side-by-side | alternatives |
| arachne_visual_snapshot Samuelfmedeiros/Arachne MCP Server | unknown | Captures URL → creates baseline (1st time) or compares | alternatives |
| arachne_visual_diff Samuelfmedeiros/Arachne MCP Server | unknown | Compares with baseline → diff + semantic verdict | alternatives |
| trigger_system_network_error io.github.vola-trebla/playwright-network-chaos-mcp | unknown | Aborts requests with an OS-level error code — simulating DNS failures, firewall blocks, etc. | alternatives |
| simulate_stateful_failure io.github.vola-trebla/playwright-network-chaos-mcp | unknown | Fails the first N requests then lets subsequent ones succeed — testing retry logic. | alternatives |
| add-accessibility io.github.oguzc/playwright-wizard-mcp | unknown | Add axe-core accessibility testing | alternatives |
| generate_report Xiangyu-Li97/prompt-injection-mcp | unknown | 生成专业测试报告 | alternatives |
| e2e_test_and_show_screenshot ezBuilder/ChatGPT To Codex | unknown | Run E2E test, open app, capture screenshots, and return inline previews | alternatives |
| test_project segentic-lab/periscope-mcp | unknown | Crawls and audits an entire site with accessibility, SEO, GEO, visual, and functionality checks. | alternatives |
| intercept_network segentic-lab/periscope-mcp | unknown | Mocks APIs and captures network responses. | alternatives |
| report_verdict io.github.piyushpathakqa/vigilis-mcp | unknown | Report a verdict on a test (pass/fail/skip). | alternatives |
| run_full_test io.github.AishwaryShrivastav/vibe-testing | unknown | Runs the complete test suite, producing a snapshot diff showing fixes, regressions, and new items since the last run | alternatives |
| test_run io.github.iVamsi/droidagentkit | unknown | Run tests. | alternatives |
| run_ui_tests janayuv/mcp-devops-server | unknown | Run Playwright UI tests | alternatives |
| interact_and_test segentic-lab/periscope-mcp | unknown | Batches 25 action types with checks in a single call. | alternatives |
| playwright io.github.Dave-London/test | unknown | Run Playwright tests with structured pass/fail output | alternatives |
| test_project io.github.segentic-lab/periscope-mcp | unknown | Crawls and audits an entire site with accessibility, SEO, GEO, visual, and functionality checks | alternatives |
| interact_and_test io.github.segentic-lab/periscope-mcp | unknown | Batches 25 action types with checks in a single call | alternatives |
| run_scenario Coding-Crashkurse/Agentic-E2E-Testing---MCP-Server | unknown | Executes a plain Scenario in the browser, records artifacts, and returns a RunResult with verdict. | alternatives |
| list_testcase io.github.testdino-inc/testdino-mcp | unknown | List test cases with comprehensive filtering (by test run, status, browser, error category, branch, environment, commit, author, spec file, | alternatives |
| debug_testcase io.github.testdino-inc/testdino-mcp | unknown | Debug a test case by aggregating historical failure data across multiple executions. Returns failure patterns, error categories, common erro | alternatives |
| list_manual_test_cases io.github.testdino-inc/testdino-mcp | unknown | Search and list manual test cases with comprehensive filtering (project, suite, status, priority, severity, type, layer, behavior, automatio | alternatives |
| update_manual_test_case io.github.testdino-inc/testdino-mcp | unknown | Update existing manual test cases (title, description, steps, status, priority, severity, type, layer, behavior, tags, custom fields, precon | alternatives |
| test_audit io.github.testdino-inc/testdino-mcp | unknown | Run a single-pass test quality audit. Fetch the server-curated prompt and branch signals, analyze the repo locally, submit the completed rep | alternatives |
| list_manual_test_suites io.github.testdino-inc/testdino-mcp | unknown | List test suite hierarchy to find suite IDs for organization. Supports filtering by parent suite. | alternatives |
| create_manual_test_suite io.github.testdino-inc/testdino-mcp | unknown | Create new test suite folders to organize test cases. Supports nested suites by providing parentSuiteId. | alternatives |
| get_release io.github.testdino-inc/testdino-mcp | unknown | Get full details for one release including dates, status, parent/root hierarchy, and rolled-up progress stats across all runs in this releas | alternatives |
| create_release io.github.testdino-inc/testdino-mcp | unknown | Create a new release with name, type, dates, and optional parent for nesting. | alternatives |
| update_release io.github.testdino-inc/testdino-mcp | unknown | Modify an existing release — name, dates, completion status, and parent. | alternatives |
| test_assert Nicolas5430/glance | unknown | Run a single assertion | alternatives |
| session_list wichaimichel85809/glance | unknown | List recorded sessions | alternatives |
| visual_baseline wichaimichel85809/glance | unknown | Save a visual baseline | alternatives |
| visual_compare wichaimichel85809/glance | unknown | Compare against baseline | alternatives |
| test_scenario_run wichaimichel85809/glance | unknown | Run a multi-step test scenario | alternatives |
| test_fill_form wichaimichel85809/glance | unknown | Auto-fill a form | alternatives |
| session_assert funkyfunc/terminal-driver-mcp | unknown | Pass/fail screen assertion with contextual diff; exact_col pins the text to a starting column. | alternatives |
| run_test funkyfunc/terminal-driver-mcp | unknown | Replay a JSON test script deterministically. | alternatives |
| oc_assert openchrome-mcp | unknown | Assert page state against an Outcome Contract. | alternatives |
| test_scenario_status wichaimichel85809/glance | unknown | Check running scenario status | alternatives |
| test_assert wichaimichel85809/glance | unknown | Run a single assertion | alternatives |
| test_auth_flow wichaimichel85809/glance | unknown | Test a login/signup flow | alternatives |
| test_watch_events wichaimichel85809/glance | unknown | Watch for DOM/network events | alternatives |
| test_stop_watch wichaimichel85809/glance | unknown | Stop watching events | alternatives |
| session_end wichaimichel85809/glance | unknown | End and save a session | alternatives |
| list_tests aliboIly/Tripwire | unknown | List all available headless tests. | alternatives |
| run_ticket Coding-Crashkurse/Agentic-E2E-Testing---MCP-Server | unknown | Executes a BugTicket in the browser, records artifacts, and returns a RunResult with verdict. | alternatives |
| validate_ticket Coding-Crashkurse/Agentic-E2E-Testing---MCP-Server | unknown | Performs semantic validation of a ticket without a browser (host allowlist, criteria coverage, brittle selectors). | alternatives |
| record_test_evidence Lrosias/yougame-plugin | unknown | Record screenshots/traces and outcomes. | alternatives |
| test_scenario_run Nicolas5430/glance | unknown | Run a multi-step test scenario | alternatives |
| test_scenario_status Nicolas5430/glance | unknown | Check running scenario status | alternatives |
| add_run adakh3/testrails-mcp | unknown | Create a new test run. | alternatives |
| qa_get_trace inSideos-designs/cowork-qa-mcp | unknown | Return the goal, every step, final URL, and final aria-snapshot — formatted for an LLM to read | alternatives |
| reticle_snapshot @reticlehq/server | unknown | Get a snapshot of the current app state | alternatives |
| reticle_query @reticlehq/server | unknown | Query the DOM or app state | alternatives |
| reticle_inspect @reticlehq/server | unknown | Inspect an element or state | alternatives |
| enhanced_start_app iflow-mcp_wolfcoming-adb_mcp_server | unknown | 增强型应用启动功能，可绕过权限限制 | alternatives |
| agent_probe @medyll/acp-team | unknown | Probes an agent to verify it works. | alternatives |
| compat_test @medyll/acp-team | unknown | Tests compatibility with an agent. | alternatives |
| genTestExpectRoleAndName @uuv/mcp-server | unknown | Verify element existence (ARIA) | alternatives |
| validate_test_case io.github.maksimsarychau/mcp-zebrunner | unknown | Validates a test case against quality rules and analysis checkpoints. | alternatives |
| verify_fix @agentlensjs/shared | unknown | Did my fix work? — waits for HMR, watches whether the error recurs | alternatives |
| start_test_session Lrosias/yougame-plugin | unknown | Start a test session with disposable players on an isolated test site. | alternatives |
| reticle_act @reticlehq/server | unknown | Perform a single action | alternatives |
| run_ui_test iflow-mcp_wolfcoming-adb_mcp_server | unknown | 执行UI测试步骤 | alternatives |
| check_element_exists iflow-mcp_wolfcoming-adb_mcp_server | unknown | 检查界面元素是否存在 | alternatives |
| tap_element_by_text iflow-mcp_wolfcoming-adb_mcp_server | unknown | 点击包含指定文本的UI元素 | alternatives |
| analyze_performance iflow-mcp_wolfcoming-adb_mcp_server | unknown | 分析应用性能 | alternatives |
| visual_inspector riccardosecchi/gem-mcp | unknown | Takes screenshots and validates UI against design expectations. | alternatives |
| validation_check validpilot/ai-verify-mcp | unknown | 检查点验证（负载时间、JS错误、HTTP错误等） | alternatives |
| validation_element validpilot/ai-verify-mcp | unknown | 元素状态验证（存在、可见、文本包含等） | alternatives |
| validation_report_export validpilot/ai-verify-mcp | unknown | 导出验证报告 | alternatives |
| e2e @autodevjapan/godd-mcp-alpha | unknown | Browser-based E2E testing (execute & verify critical user flows) | alternatives |
| get_manual_test_case io.github.testdino-inc/testdino-mcp | unknown | Get detailed information about a specific manual test case including steps, custom fields, preconditions, postconditions, and all metadata. | alternatives |
| create_manual_test_case io.github.testdino-inc/testdino-mcp | unknown | Create new manual test cases with steps, preconditions, postconditions, and metadata (priority, severity, type, layer, behavior). | alternatives |
| get_test_scenarios lucascortazz/MCP Mobile Automation Server | unknown | Get a list of available test scenarios from feature files. | alternatives |
| assert_text wooter-s/weixin-devtools-mcp | unknown | 断言元素文本 | alternatives |
| run_tests_on_browserstack io.github.browserstack/mcp-server | unknown | Run automated tests on BrowserStack. | alternatives |
| test-recorder io.github.steve228uk/metro-mcp | unknown | Record interactions and generate Appium, Maestro, or Detox tests | alternatives |
| verify_determinism industrial-aiops/OT-AIops | unknown | Run a deterministic verification suite against a pinned dataset | alternatives |
| readiness industrial-aiops/OT-AIops | unknown | Check which scenarios are ready to run and identify gaps | alternatives |
| arachne_visual_list Samuelfmedeiros/Arachne MCP Server | unknown | Lists baselines + status | alternatives |
| reset com.mock-server/mockserver | unknown | Reset MockServer to its initial state, clearing all expectations and logs | alternatives |
| create_exploratory_test_case qatouch-mcp-server | unknown | Create a QA Touch exploratory-session test case without structured steps | alternatives |
| create_requirement qatouch-mcp-server | unknown | Create a requirement in a QA Touch project requirement document | alternatives |
| create_text_test_case qatouch-mcp-server | unknown | Create a QA Touch test case using the text template endpoint | alternatives |
| list_modules qatouch-mcp-server | unknown | Get all modules from a project | alternatives |
| list_requirement_documents qatouch-mcp-server | unknown | List requirement documents for a QA Touch project | alternatives |
| assert_visual mi60dev/visionaire-engine | unknown | 17-type assertion grammar — PASS/FAIL verdicts with measured pixels, offending uids, and re-runnable named suites | alternatives |
| arachne_visual_approve Samuelfmedeiros/Arachne MCP Server | unknown | Promotes current → new baseline | alternatives |
| verify_ui_flow @rolepod/uiproof | unknown | Drive a session through steps, evaluate assertions (incl. console errors / failed requests / specific request made / response status), save | alternatives |
| browser_run_test @pablovitasso/szkrabok | unknown | Run .spec.js tests via CDP. Requires scaffold_init and open session. | alternatives |
| assert io.github.rn-devtools-hub/rn-devtools-hub | unknown | Proves a step: element kinds retry, event kinds catch a request that failed silently, a console error, an unhandled rejection. | alternatives |
| run_test_sequence Xiangyu-Li97/prompt-injection-mcp | unknown | 执行预定义测试流程 | alternatives |
| generate_custom_payload Xiangyu-Li97/prompt-injection-mcp | unknown | 基于模板生成自定义测试用例 | alternatives |
| analyze_response Xiangyu-Li97/prompt-injection-mcp | unknown | 智能分析系统响应 | alternatives |
| simulate_api_failure io.github.vola-trebla/playwright-network-chaos-mcp | unknown | Intercepts requests matching a pattern and forces them to return an error status code. Checks if the app shows a fallback UI. | alternatives |
| inject_latency io.github.vola-trebla/playwright-network-chaos-mcp | unknown | Adds artificial delay to matching requests. Checks if loading states appear while the app waits. | alternatives |
| simulate_network_drop io.github.vola-trebla/playwright-network-chaos-mcp | unknown | Aborts requests mid-flight after a delay — simulating connection loss. | alternatives |
| prove_result rn-devtools-hub | unknown | Proves a step's result using assertions instead of screenshots (e.g., check a request failed silently). | alternatives |
| wait_on_event rn-devtools-hub | unknown | Waits for a specific app event to occur instead of sleeping. | alternatives |
| freeze_clock rn-devtools-hub | unknown | Freezes the JavaScript clock in the runtime. | alternatives |
| freeze_network rn-devtools-hub | unknown | Freezes network requests in the runtime. | alternatives |
| set_store_state rn-devtools-hub | unknown | Sets the app's store to an exact state directly. | alternatives |
| get_test_metadata io.github.vola-trebla/playwright-trace-decoder-mcp | unknown | Returns browser, platform, viewport, test title, wall-clock start time | alternatives |
| run_probe io.github.swerve-hoe/ozma | unknown | Run a test call to validate an API fits your needs | alternatives |
As of the latest check, Glimind tracks 146 testing AI agent (MCP) tools, of which 16 are healthy right now. The table below ranks them live-first by real-time reliability. Glimind rates each neutrally (0–100) from safe liveness probes plus privacy-clean real-usage outcomes — see each tool's live page for its current score and a working alternative if it's down.
Ranked live-first by current verdict (healthy → degraded → down), then by the neutral reliability score. Glimind sells no tools, so the ranking is unconflicted.
Every tool here links to its live alternatives — capability-matched substitutes that are healthy now. Or query https://glimind.com/v1/alternatives/{toolId}.
Live data via MCP/REST. Neutral ratings — Glimind only measures.