Skip to main content
mcpSource-backed
HttpRunner logo

HttpRunner UIXT MCP Server

MCP server from HttpRunner that exposes UIXT device and browser automation tools for Android, iOS, Harmony, and Web testing through the `hrp mcp-server` command.

by debugtalk · submitted by oktofeesh1·added 2026-06-06·
Review first review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Source URLs
https://raw.githubusercontent.com/httprunner/httprunner/master/docs/uixt/mcp-server.md, https://github.com/httprunner/httprunner
Brand
HttpRunner
Brand domain
httprunner.com
Brand asset source
brandfetch
Safety notes
HttpRunner UIXT MCP Server can control real devices and browsers through taps, swipes, text input, hardware buttons, selectors, OCR, CV, and AI action tools., App tools can launch, terminate, cold launch, install, uninstall, clear data, and inspect foreground apps on connected devices., Screen tools can capture screenshots, screen recordings, screen size, and UI hierarchy/source data., Media and utility tools can modify test-device albums, close popups, wait randomly, and interact with system UI state., Simulated gesture options and anti-risk-style behavior should be used only in authorized test automation environments., Require human review before running actions against logged-in accounts, payment flows, device settings, production apps, or customer data.
Privacy notes
Screenshots, screen recordings, UI hierarchy, package names, foreground app names, OCR text, selector data, and logs can expose sensitive app or account state., Connected device identifiers, serial numbers, app package names, browser pages, and test artifacts may be visible to the MCP client., Input and paste actions can expose credentials, one-time codes, chat text, forms, or clipboard-like data if used on personal sessions., Test reports, MCP responses, and debugging logs may retain captured UI state after the session ends., Keep test devices resettable, avoid personal accounts, and isolate artifacts produced by automated UI runs.
Author
debugtalk
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-06

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

63

Baseline

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Needs review

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done
  • Source provenance statusRequired

    Marked as source-backed.

    Done
  • Metadata reviewed

    No reviewed flag detected in metadata.

    Pending

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done
  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done
  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done
  • Package verification flag

    No package verification flag provided.

    Pending
  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending
  • Baseline comparison available

    No baseline peer selected yet.

    Pending
  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

CLI install

Copy-ready — paste the snippet to get started.

30 minutes

Adoption plan

Balanced adoption plan

Current risk score 24/100. Use staged verification before broader rollout.

Risk 24

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done
  • Confirm metadata review state

    No review metadata found; increase manual validation.

    Pending
  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done
  • Review privacy notesRequired

    Privacy notes are present.

    Done
  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending
  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending
  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Missing required evidence: Metadata review. Risk score 31.

Risk 31

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Missing

Review metadata is missing.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required gaps: Metadata review

Decision timeline

Decision timeline · balanced

Blocking gaps: Check metadata review status. Risk 28.

Risk 28

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is missing.

Pending

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

Blockers: Check metadata review status

Prerequisite readiness

Prerequisite readiness

5 prerequisites to line up before setup. Includes a review or approval gate.

0/5 ready
Install & runtime2Configuration1Review & approval1General130 minutes

Safety & privacy surface

Safety & privacy surface

6 safety and 5 privacy notes across 6 risk areas. Review closely: credentials & tokens, permissions & scopes, network access.

6 areas
  • SafetyNetwork accessHttpRunner UIXT MCP Server can control real devices and browsers through taps, swipes, text input, hardware buttons, selectors, OCR, CV, and AI action tools.
  • SafetyExecution & processesApp tools can launch, terminate, cold launch, install, uninstall, clear data, and inspect foreground apps on connected devices.
  • SafetyGeneralScreen tools can capture screenshots, screen recordings, screen size, and UI hierarchy/source data.
  • SafetyGeneralMedia and utility tools can modify test-device albums, close popups, wait randomly, and interact with system UI state.
  • SafetyPermissions & scopesSimulated gesture options and anti-risk-style behavior should be used only in authorized test automation environments.
  • SafetyExecution & processesRequire human review before running actions against logged-in accounts, payment flows, device settings, production apps, or customer data.
  • PrivacyData retentionScreenshots, screen recordings, UI hierarchy, package names, foreground app names, OCR text, selector data, and logs can expose sensitive app or account state.
  • PrivacyGeneralConnected device identifiers, serial numbers, app package names, browser pages, and test artifacts may be visible to the MCP client.
  • PrivacyCredentials & tokensInput and paste actions can expose credentials, one-time codes, chat text, forms, or clipboard-like data if used on personal sessions.
  • PrivacyCredentials & tokensTest reports, MCP responses, and debugging logs may retain captured UI state after the session ends.
  • PrivacyExecution & processesKeep test devices resettable, avoid personal accounts, and isolate artifacts produced by automated UI runs.

Disclosure: Apache-2.0 open source MCP server within HttpRunner v5. The MCP command is source-backed in the current repository; build from source or follow upstream v5 installation guidance when available.

Safety notes

  • HttpRunner UIXT MCP Server can control real devices and browsers through taps, swipes, text input, hardware buttons, selectors, OCR, CV, and AI action tools.
  • App tools can launch, terminate, cold launch, install, uninstall, clear data, and inspect foreground apps on connected devices.
  • Screen tools can capture screenshots, screen recordings, screen size, and UI hierarchy/source data.
  • Media and utility tools can modify test-device albums, close popups, wait randomly, and interact with system UI state.
  • Simulated gesture options and anti-risk-style behavior should be used only in authorized test automation environments.
  • Require human review before running actions against logged-in accounts, payment flows, device settings, production apps, or customer data.

Privacy notes

  • Screenshots, screen recordings, UI hierarchy, package names, foreground app names, OCR text, selector data, and logs can expose sensitive app or account state.
  • Connected device identifiers, serial numbers, app package names, browser pages, and test artifacts may be visible to the MCP client.
  • Input and paste actions can expose credentials, one-time codes, chat text, forms, or clipboard-like data if used on personal sessions.
  • Test reports, MCP responses, and debugging logs may retain captured UI state after the session ends.
  • Keep test devices resettable, avoid personal accounts, and isolate artifacts produced by automated UI runs.

Prerequisites

  • Go 1.23 or newer for building the current v5 CLI from source.
  • A test Android, iOS, Harmony, or browser automation environment configured for HttpRunner UIXT.
  • A trusted MCP client that can launch local stdio servers.
  • Review of ADB, go-ios, WebDriver, OCR, computer-vision, and AI-action dependencies required by your target platform.
  • Dedicated test devices, simulators, or browsers rather than personal or production devices.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
30 minutes
Difficulty
advanced
Tool listing metadata
Disclosure
Apache-2.0 open source MCP server within HttpRunner v5. The MCP command is source-backed in the current repository; build from source or follow upstream v5 installation guidance when available.
Full copyable content
{
  "mcpServers": {
    "httprunner-uixt": {
      "command": "hrp",
      "args": ["mcp-server"]
    }
  }
}

About this resource

Content

HttpRunner UIXT MCP Server exposes HttpRunner's UIXT automation layer through a stdio MCP server. It gives Claude and other MCP clients structured tools for discovering devices, selecting a test target, tapping, swiping, entering text, controlling apps, capturing screen state, and running browser actions.

Use it when Claude needs supervised access to a prepared UI testing environment, not when an assistant should freely control a personal phone, desktop browser, or production account.

Source Review

These sources were reviewed on 2026-06-06. Prefer the live repository, MCP server docs, license, README, Go module, CLI entrypoint, MCP command source, UIXT server source, Cobra command docs, and tool documentation for current setup and behavior details.

Features

  • Start a stdio MCP server with hrp mcp-server.
  • Discover and select Android, iOS, Harmony, simulator, or browser targets.
  • Tap by relative coordinates, absolute coordinates, OCR text, computer vision, or selectors.
  • Swipe, drag, double tap, press buttons, go home, and go back.
  • Enter text, set input method behavior, and use simulated input actions.
  • Launch, terminate, cold launch, install, uninstall, clear, and inspect apps.
  • Capture screenshots, screen recordings, screen size, and UI hierarchy/source.
  • Run browser actions such as selector hover, selector tap, secondary click, and closing tabs.
  • Use higher-level AI action and start-to-goal workflows when the target environment is approved for autonomous testing.

Installation

The current MCP server is part of HttpRunner v5 source. Build the CLI from the repository:

git clone https://github.com/httprunner/httprunner.git
cd httprunner
go build -o hrp ./cmd/cli

Then configure your MCP client to launch the hrp mcp-server command:

{
  "mcpServers": {
    "httprunner-uixt": {
      "command": "hrp",
      "args": ["mcp-server"]
    }
  }
}

Make sure the built hrp binary is on PATH for the MCP client process, or use the full path to the binary in your local configuration.

Use Cases

  • Let Claude inspect connected test devices before choosing a target.
  • Reproduce a mobile UI bug through controlled taps, swipes, and screenshots.
  • Launch a test app, clear state, and capture the resulting UI hierarchy.
  • Automate a browser flow using selectors and screenshots in a supervised test session.
  • Generate exploratory UI actions against a simulator, then convert stable steps into repeatable HttpRunner test assets.

Safety and Privacy

HttpRunner UIXT MCP Server is powerful device automation. Use it only with authorized test devices, simulators, or browsers. Keep production accounts, personal devices, payment flows, device settings, and customer data outside the agent-controlled environment unless the task has explicit approval and rollback coverage.

Review screenshots, recordings, package lists, UI hierarchy output, OCR text, selector data, and logs before sharing them. Reset devices or simulators between runs when tests may expose credentials, private messages, or internal app state.

Source citations

Add this badge to your README

Show that HttpRunner UIXT MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/httprunner-uixt-mcp-server.svg)](https://heyclau.de/entry/mcp/httprunner-uixt-mcp-server)

How it compares

HttpRunner UIXT MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

1 trust signal differ across this comparison (Submitter).

Field

MCP server from HttpRunner that exposes UIXT device and browser automation tools for Android, iOS, Harmony, and Web testing through the `hrp mcp-server` command.

Open dossier

Official MCP server for agent-device, Callstack's device automation CLI for inspecting, controlling, debugging, recording, and collecting evidence from iOS, Android, TV, macOS, Linux, React Native, Expo, Flutter, and native apps.

Open dossier

Unity MCP server, plugin, CLI, and skill generator for controlling Unity Editor and runtime projects from MCP clients through built-in game-dev tools.

Open dossier

Access AI-optimized Android development guides from Claude — search and retrieve SKILL.md content covering Jetpack Compose, Navigation 3, CameraX, AGP 9, App Functions, Edge-to-Edge, Android Profilers, XR, Google Play, and the Android CLI — with the Android Skills MCP server.

Open dossier
Next steps
Trust
Review statusNot reviewedNot reviewedNot reviewedNot reviewed
Package trustPackage not verifiedPackage not verifiedPackage not verifiedPackage not verified
Source provenanceSource-backedSource-backedSource-backedSource-backed
SubmitterDiffersoktofeesh1oktofeesh1oktofeesh1
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
BrandHttpRunner logoHttpRunneragent-device logoagent-deviceAI Game Developer logoAI Game DeveloperGoogle logoGoogle
Categorymcpmcpmcpmcp
SourceSource-backedSource-backedSource-backedSource-backed
AuthordebugtalkCallstackIvan MurzakJaewoong Eum (skydoves)
Added2026-06-062026-06-062026-06-062026-06-18
Platforms
Harness
Source repo
Safety notesHttpRunner UIXT MCP Server can control real devices and browsers through taps, swipes, text input, hardware buttons, selectors, OCR, CV, and AI action tools. App tools can launch, terminate, cold launch, install, uninstall, clear data, and inspect foreground apps on connected devices. Screen tools can capture screenshots, screen recordings, screen size, and UI hierarchy/source data. Media and utility tools can modify test-device albums, close popups, wait randomly, and interact with system UI state. Simulated gesture options and anti-risk-style behavior should be used only in authorized test automation environments. Require human review before running actions against logged-in accounts, payment flows, device settings, production apps, or customer data.Agent Device MCP exposes structured tools backed by `AgentDeviceClient`; the docs state it does not expose generic shell execution over MCP. Tools and CLI workflows can open apps, inspect UI, tap, type, scroll, perform gestures, wait, assert state, handle alerts, and close sessions. Evidence workflows can capture screenshots, recordings, logs, traces, network traffic, performance samples, crash context, React profiles, and replay files. Mutating commands should run serially against one session, and separate sessions or devices should be used for parallel work. Prefer dedicated test devices or simulators, and require approval before entering credentials, submitting forms, changing settings, installing apps, sending messages, or touching production accounts.AI Game Developer can create, move, copy, modify, and delete Unity assets, scenes, GameObjects, components, scripts, packages, and generated project files. Tools include dynamic C# script execution, C# reflection method lookup and calls, package installation/removal, Unity test execution, editor state changes, play mode control, screenshots, and profiler access. The MCP server supports streamable HTTP and stdio; HTTP deployments should require a bearer token and stay bound to trusted interfaces. Server variables include optional authorization and webhook settings; webhook endpoints can receive tool, prompt, resource, connection, and authorization events. Unity runtime connections can expose compiled game state or in-game behavior to an MCP client, not just editor-only project data. Use source control, backups, tool filtering, and explicit review before allowing destructive tools such as asset deletion, package removal, script execution, or reflection calls.The server runs entirely offline — no network requests are made during queries. All skill content is bundled with the npm package.
Privacy notesScreenshots, screen recordings, UI hierarchy, package names, foreground app names, OCR text, selector data, and logs can expose sensitive app or account state. Connected device identifiers, serial numbers, app package names, browser pages, and test artifacts may be visible to the MCP client. Input and paste actions can expose credentials, one-time codes, chat text, forms, or clipboard-like data if used on personal sessions. Test reports, MCP responses, and debugging logs may retain captured UI state after the session ends. Keep test devices resettable, avoid personal accounts, and isolate artifacts produced by automated UI runs.Screenshots, recordings, traces, logs, network dumps, replay files, reports, UI snapshots, typed input, and React profiles can contain private UI state, tokens, request data, customer information, or credentials. macOS, iOS, Android, and TV automation can expose local app state, notifications, device names, package identifiers, app content, system dialogs, and permission prompts. Network inspection artifacts may include headers, payloads, session identifiers, URLs, and API data; review before sharing or committing. Interactive CLI runs may check npm for newer package versions unless `AGENT_DEVICE_NO_UPDATE_NOTIFIER=1` is set.Tool calls may expose Unity project paths, asset names, scene hierarchy, serialized object data, scripts, logs, screenshots, profiler metrics, test output, package metadata, and runtime state. MCP config files and Unity plugin config can contain server URLs, connection modes, bearer tokens, authorization settings, enabled tool IDs, and cloud or local endpoint details. Optional webhooks can receive tool, prompt, resource, connection, authorization, and token-bearing request data. Screenshots from Game View, Scene View, cameras, or isolated GameObjects may include proprietary artwork, level design, UI, debug overlays, or unreleased game content. Generated skills and AI-client configuration files can reveal available tools, project structure, installed packages, and local workflow assumptions.No API keys, user data, or query content is sent to any external service. All lookups happen locally against the bundled skill snapshot.
Prerequisites
  • Go 1.23 or newer for building the current v5 CLI from source.
  • A test Android, iOS, Harmony, or browser automation environment configured for HttpRunner UIXT.
  • A trusted MCP client that can launch local stdio servers.
  • Review of ADB, go-ios, WebDriver, OCR, computer-vision, and AI-action dependencies required by your target platform.
  • Node.js 22 or newer and `agent-device` installed globally or project-locally.
  • Xcode tooling for iOS, tvOS, or macOS targets, or Android SDK and ADB for Android targets.
  • Device, simulator, emulator, TV, macOS, or Linux desktop target that the agent is allowed to automate.
  • Required local permissions such as Android device trust, iOS Developer Mode, macOS Accessibility, and Screen Recording where applicable.
  • Unity project using Unity 2022.3 or newer for the current package metadata.
  • Unity Hub or a local Unity Editor installation.
  • Node.js 20.19 or newer, or Node.js 22.12 or newer, for `unity-mcp-cli`.
  • An MCP client such as Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI, GitHub Copilot, Cline, or another supported client.
  • Node.js with `npx` available.
  • An MCP client such as Claude Code or Claude Desktop.
Install
git clone https://github.com/httprunner/httprunner.git && cd httprunner && go build -o hrp ./cmd/cli
claude mcp add --transport stdio --scope user agent-device -- agent-device mcp
npm install -g unity-mcp-cli && unity-mcp-cli install-plugin ./MyUnityProject
claude mcp add android-skills -- npx -y android-skills-mcp
Config
{
  "mcpServers": {
    "httprunner-uixt": {
      "command": "hrp",
      "args": [
        "mcp-server"
      ],
      "type": "stdio"
    }
  }
}
{
  "mcpServers": {
    "agent-device": {
      "command": "agent-device",
      "args": ["mcp"]
    }
  }
}
Manual-only setup:
npm install -g unity-mcp-cli
unity-mcp-cli install-plugin ./MyUnityProject
unity-mcp-cli open ./MyUnityProject
{
  "mcpServers": {
    "android-skills": {
      "command": "npx",
      "args": ["-y", "android-skills-mcp"]
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.