Which integrations are available for this server?

Allows AI agents to manipulate HarmonyOS devices, such as launching apps, through MCP tools.

How do I use HarmonyOS MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@HarmonyOS MCP Server Launch the settings app on my phone" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

HarmonyOS MCP Server

by XixianLiang

Overview Schema Source Related Servers Discussions Admin

Python

Local

Intro

This is a MCP server for manipulating harmonyOS Device.

https://github.com/user-attachments/assets/7af7f5af-e8c6-4845-8d92-cd0ab30bfe17

Related MCP server: matter-mcp-server

Quick Start

Installation

Clone this repo

git clone https://github.com/XixianLiang/HarmonyOS-mcp-server.git
cd HarmonyOS-mcp-server

Setup the envirnment.

uv python install 3.13
uv sync

Usage

1.Claude Desktop

You can use Claude Desktop to try our tool.

2.Openai SDK

You can also use openai-agents SDK to try the mcp server. Here's an example

"""
Example: Use Openai-agents SDK to call HarmonyOS-mcp-server
"""
import asyncio
import os

from agents import Agent, Runner, gen_trace_id, trace
from agents.mcp import MCPServerStdio, MCPServer

async def run(mcp_server: MCPServer):
    agent = Agent(
        name="Assistant",
        instructions="Use the tools to manipulate the HarmonyOS device and finish the task.",
        mcp_servers=[mcp_server],
    )

    message = "Launch the app `settings` on the phone"
    print(f"Running: {message}")
    result = await Runner.run(starting_agent=agent, input=message)
    print(result.final_output)


async def main():

    # Use async context manager to initialize the server
    async with MCPServerStdio(
        params={
            "command": "<...>/bin/uv",
            "args": [
                "--directory",
                "<...>/harmonyos-mcp-server",
                "run",
                "server.py"
            ]
        }
    ) as server:
        trace_id = gen_trace_id()
        with trace(workflow_name="MCP HarmonyOS", trace_id=trace_id):
            print(f"View trace: https://platform.openai.com/traces/trace?trace_id={trace_id}\n")
            await run(server)

if __name__ == "__main__":
    asyncio.run(main())

3.Langchain

You can use LangGraph, a flexible LLM agent framework to design your workflows. Here's an example

"""
langgraph_mcp.py
"""

server_params = StdioServerParameters(
    command="/home/chad/.local/bin/uv",
    args=["--directory",
          ".",
          "run",
          "server.py"],
    
)


#This fucntion would use langgraph to build your own agent workflow
async def create_graph(session):
    llm = ChatOllama(model="qwen2.5:7b", temperature=0)
    #!!!load_mcp_tools is a langchain package function that integrates the mcp into langchain.
    #!!!bind_tools fuction enable your llm to access your mcp tools
    tools = await load_mcp_tools(session)
    llm_with_tool = llm.bind_tools(tools)

    
    system_prompt = await load_mcp_prompt(session, "system_prompt")
    prompt_template = ChatPromptTemplate.from_messages([
        ("system", system_prompt[0].content),
        MessagesPlaceholder("messages")
    ])
    chat_llm = prompt_template | llm_with_tool

    # State Management
    class State(TypedDict):
        messages: Annotated[List[AnyMessage], add_messages]

    # Nodes
    def chat_node(state: State) -> State:
        state["messages"] = chat_llm.invoke({"messages": state["messages"]})
        return state

    # Building the graph
    # graph is like a workflow of your agent.
    #If you want to know more langgraph basic,reference this link (https://langchain-ai.github.io/langgraph/tutorials/get-started/1-build-basic-chatbot/#3-add-a-node)
    graph_builder = StateGraph(State)
    graph_builder.add_node("chat_node", chat_node)
    graph_builder.add_node("tool_node", ToolNode(tools=tools))
    graph_builder.add_edge(START, "chat_node")
    graph_builder.add_conditional_edges("chat_node", tools_condition, {"tools": "tool_node", "__end__": END})
    graph_builder.add_edge("tool_node", "chat_node")
    graph = graph_builder.compile(checkpointer=MemorySaver())
    return graph





async def main():
    async with stdio_client(server_params) as (read, write):
        async with ClientSession(read, write) as session:
            await session.initialize()

            config = RunnableConfig(thread_id=1234,recursion_limit=15)
            # Use the MCP Server in the graph
            agent = await create_graph(session)

            while True:
                message = input("User: ")
                try:
                    response = await agent.ainvoke({"messages": message}, config=config)
                    print("AI: "+response["messages"][-1].content)
                except RecursionError:
                    result = None
                    logging.error("Graph recursion limit reached.")


if __name__ == "__main__":
    asyncio.run(main())

Write the system prompt in server.py

"""
server.py
"""
@mcp.prompt()
def system_prompt() -> str:
    """System prompt description"""
    return """
    You are an AI assistant use the tools if needed.
    """

Use load_mcp_prompt function to get your prompt from mcp server.

"""
langgraph_mcp.py
"""
prompts = await load_mcp_prompt(session, "system_prompt")

Available Tools

16 tools

clickB

click the given coordinate Args: center: a string like "(x, y)", sample: "(227, 168)"

ParametersJSON Schema

Name	Required	Description	Default
`center`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.1/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It fails to disclose basic behaviors like what happens with out-of-bounds coordinates, click duration, or whether it's a single tap, leaving significant ambiguity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Short and front-loaded with the core action. The Args structure is neatly formatted, though the description is very brief.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple click tool, the description is adequate but misses key context: coordinate system origin (likely screen coordinates), units (pixels), and whether the action waits for a result. Output schema exists but return behavior is not described.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Provides explicit format and example for the 'center' parameter ('(x, y)' format), which adds significant meaning beyond the schema's bare string type. Schema coverage is 0%, so this compensation is critical.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (click) and the target (given coordinate). It effectively distinguishes from sibling tools like long_click and swipe by specifying coordinate input.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives (e.g., long_click, tap by UI element). Missing context for appropriate use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

current_appA

Get the current foreground application information.

Returns: Tuple[str, str]: A tuple contain the package_name andpage_name of the foreground application. If no foreground application is found, returns (None, None).

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description fully discloses the behavior: it returns a tuple of package_name and page_name, and returns (None, None) if no foreground app exists. This covers the main behavioral trait beyond the input schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise (two sentences) and front-loads the main purpose. It efficiently covers the return types and edge case. Minor verboseness in the Returns section could be tightened but overall well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no parameters, a clear output description, and an explicit edge case, the description is fully complete. The agent knows exactly what to expect and when to use the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the description does not need to add parameter meaning. Baseline for 0 params is 4, and the description adds no redundant parameter info.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly specifies the action 'Get' and the resource 'current foreground application information'. It uniquely identifies the tool among siblings like launch_app and list_app, as no other tool provides the foreground app info.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use or alternative guidance is provided. However, the context signals show sibling tools like launch_app and list_app, so usage is implied for checking the current visible app. Lack of exclusions or when-not-to-use prevents a higher score.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_screenshotA

Takes a screenshot of the device and returns it. Returns: Image: the screenshot

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A3.6/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavioral traits. It states that the tool returns an Image, but omits potential side effects (e.g., no indication if it requires special permissions or if it might fail in certain states). As a non-destructive operation, the lack of detailed disclosure is acceptable but not exceptional.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise, with one sentence and a return value note. However, it could be structured slightly better by explicitly listing the return type in a more prominent way.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (no parameters, straightforward action), the description is minimally complete. It explains what it does and what it returns, but lacks context like when to use it or any caveats.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has no parameters, so the description does not need to explain them. The baseline for zero parameters is 4, and the description does not attempt to add param info beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Takes a screenshot' and the resource 'device', making the purpose unambiguous. It distinguishes itself from sibling tools like 'click' or 'media_next' by focusing on screenshot capture.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, limitations, or when not to use it (e.g., if the device is locked or if a screenshot is already available).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_uilayoutA

Retrieves information about clickable elements in the current UI. Returns a formatted string containing details about each clickable element, including its text, content description, bounds, and center coordinates.

Returns: str: A formatted list of clickable elements with their properties

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.3/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description bears the full burden. It describes the return format and content but does not explicitly state that the tool is read-only or has no side effects. The behavior is implied but could be more explicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: two sentences plus a return type line. It front-loads the purpose and includes essential details without any unnecessary repetition or verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given there are no parameters and an output schema exists, the description fully explains what the tool does and what the return value contains. It is complete and sufficient for the agent to understand the tool's purpose and output.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has no parameters, and the schema description coverage is 100%. The description adds no parameter info beyond the schema, which is acceptable. Baseline for zero parameters is 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves information about clickable elements in the current UI. It uses specific verbs and resources ('retrieves information about clickable elements') and distinguishes itself from sibling tools like click or get_screenshot.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for using the tool (retrieving UI element info) but does not explicitly mention when not to use it or alternatives. However, the purpose is straightforward and the context is clear enough for an agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

input_textC

input text to the given coordinate Args: center: a string like "(x, y)", sample: "(227, 168)" text: the text to input

ParametersJSON Schema

Name	Required	Description	Default
`center`	Yes
`text`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

C2.8/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description offers minimal behavioral information. It does not disclose what happens on invalid coordinates, whether text appends or replaces, or if any special characters are supported. Without annotations, this is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise but lacks a proper structure. It reads like a code docstring rather than a formal tool description. It could be better formatted with clear sections.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema (not shown), return values are not required in the description. However, the description omits essential behavioral context, such as error handling or interaction with the UI, leaving gaps for a simple but functional tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage, so the description's parameter explanations add value. The center parameter includes an example format, and text is described briefly. However, more detail on text restrictions would improve clarity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool inputs text at a given coordinate, which distinguishes it from sibling tools like click or long_click. However, it does not explicitly contrast with alternatives, preventing a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, such as when text input is needed versus clicking a field. The description lacks context for appropriate usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

launch_appC

launch app accrodingt to the given package name. Args: package_name: the package name of the package.

ParametersJSON Schema

Name	Required	Description	Default
`package_name`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

C2.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description fails to disclose behavioral aspects like error handling (e.g., if package not found), whether it brings app to foreground, or if it checks installation state.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short but includes a typo ('accrodingt') and a non-standard 'Args:' format. It is front-loaded but lacks structure and clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

While an output schema exists, the description does not explain launch behavior, prerequisites, or return values. For an action tool, more context is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%. The description adds only 'the package name of the package', which is a tautology of the parameter name and provides no additional meaning or usage guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'launch app according to the given package name', providing a clear verb and resource. It is distinguishable from sibling tools like stop_app or list_app, though no explicit differentiation is made.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool over alternatives, no prerequisites or exclusions. The description simply states the function.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_appA

Get all installed packages on the device Returns: A list of all installed packages on the device as a string

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are available, so the description carries the full burden. It discloses the return type (a string of all installed packages) but does not mention whether system apps are included, performance impact, or authentication needs. The output schema exists (context confirmed) but the description's return note is still helpful.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with two sentences, clearly stating the action and the return value. No extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a parameterless tool with an output schema (confirmed by context), the description fully explains what the tool does and what it returns. It is complete for the agent to invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are no parameters, and schema coverage is 100%. The description adds no parameter-specific information, but per guidelines, baseline is 4 for zero parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get' and the resource 'all installed packages', which is distinct from sibling tools like click, launch_app, and media controls, making it easy for an agent to select.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool compared to alternatives. For instance, it doesn't mention that the result can be used to obtain package names for launch_app or stop_app, or any prerequisites or restrictions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

long_clickB

long click the given coordinate Args: center: a string like "(x, y)", sample: "(227, 168)"

ParametersJSON Schema

Name	Required	Description	Default
`center`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description gives minimal behavioral insight. It does not disclose what happens after a long click (e.g., context menu, press-and-hold), error handling, or whether it blocks until release.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise but includes an 'Args' section that is redundant with the single parameter. Still, it is front-loaded with the action statement.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema exists (but not shown), the description may be adequately complete for a simple action, but it lacks any context about return values or side effects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds format guidance for the 'center' parameter with a concrete example '(x, y)' and sample '(227, 168)', which goes beyond the schema's type-only definition. However, it could specify coordinate system origin or bounds.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it performs a 'long click' at a given coordinate, distinguishing it from the sibling 'click' tool. The verb (long click) and resource (coordinate) are specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like 'click' or 'swipe'. No conditions, prerequisites, or exclusions are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

media_nextC

play the next media

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations are absent, so the description must fully disclose behavior. It only indicates 'play next media' without stating if playback automatically starts, stops current media, or other side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very short (one sentence) but lacks critical details, making it under-specified. It earns its place by stating purpose, but could be more informative without adding length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity and the presence of an output schema, the description omits important behavioral context, such as whether it always plays or just skips. The sibling set suggests media controls, but completeness is low.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero parameters (100% coverage), and the description adds no parameter info. Per rule, 0 parameters warrants a baseline score of 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'play the next media,' which clearly identifies the verb and resource. It distinguishes from sibling 'media_previous' by naming, but does not differentiate from 'media_play_pause' beyond the name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No usage context or alternatives are provided. The description does not specify when to use this tool versus siblings like 'media_play_pause' or 'media_previous'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

media_play_pauseA

Play or pause media on the phone.

Sends the media play/pause keycode to control any currently active media. Can be used to play music or videos that were recently playing.

Returns: str: Success message if the command was sent, or an error message if the command failed.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, but the description explains that it sends a keycode and returns success/error. It implies a toggle action without explicit side-effect details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise with three clear sentences, no wasted words, and front-loads the primary action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no parameters and a simple return type, the description fully explains its function and output, making it complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist (schema coverage 100%), so the description cannot add parameter details. The baseline 4 is appropriate as it adds return value semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'play or pause' and the resource 'media', which distinguishes it from sibling tools like media_next and media_previous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context ('Can be used to play music or videos that were recently playing') but does not explicitly exclude other scenarios or mention alternatives among siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

media_previousB

play the previous media

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.1/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It merely says 'play', but does not disclose side effects (e.g., whether it stops current media, if it works only when media is playing, or if it's idempotent).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise (4 words) and front-loaded. It is appropriate for a simple action, though it could add a bit more context without becoming verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity (0 parameters, output schema exists), the description is adequate but minimal. It does not explain return values or behavior at boundaries (e.g., if already at first track). Sibling tools are present, providing context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are no parameters (schema coverage 100%), so the description does not need to add parameter info. Baseline for 0 parameters is 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'play the previous media' clearly states the action and resource. It distinguishes from sibling tools like media_next and media_play_pause. However, it could be more specific about what 'previous' means (e.g., previous track).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like media_next or media_play_pause. It does not mention prerequisites or context for usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

stop_appD

ParametersJSON Schema

Name	Required	Description	Default
`package_name`	Yes

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

swipeD

ParametersJSON Schema

Name	Required	Description	Default
`x1`	Yes
`y1`	Yes
`x2`	Yes
`y2`	Yes
`speed`	No

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

volume_downB

turn down the volume

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.1/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided; description only says 'turn down the volume' without specifying step size, whether it is relative or absolute, or behavior at minimum volume.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise (4 words) but lacks additional context; more could be added without being verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no parameters and clear sibling tools, description is minimally adequate but does not explain output or behavior beyond the basic action.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, so schema coverage is 100%; description does not add parameter meaning but baseline is 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it turns down the volume, distinguishing it from siblings like volume_up (increase) and volume_mute (mute).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives, or any conditions/exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

volume_muteC

mute the volume

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries the full burden of behavioral disclosure. It does not specify whether muting toggles or sets a state, if it affects system or media volume, or any side effects. This is insufficient for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise (3 words), but it adds no value beyond the tool name 'volume_mute'. It does not earn its place as it is redundant and under-specified.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has an output schema (unknown but present) and no parameters, so the description's minimal nature is somewhat acceptable. However, it lacks context about scope (system vs media), which is important given sibling tools like volume_down and volume_up.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are no parameters, so schema coverage is 100% implicitly. The description adds no parameter information, but according to the rule, no parameters warrants a baseline of 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the action ('mute') and resource ('volume'), which is specific enough. However, it does not differentiate from siblings like volume_down or volume_up, but the verb 'mute' is distinct enough.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives such as volume_down or media_play_pause. The description lacks any context for appropriate usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

volume_upB

turn up the volume

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.3/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description does not disclose any behavioral traits beyond the action. It fails to mention any permissions required, whether the action is reversible, or any side effects such as impact on other audio settings.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with a single phrase that fully captures the tool's purpose. Every word is meaningful and no information is wasted, making it well-structured for such a simple tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (no parameters, output schema exists), the description is minimally adequate but does not elaborate on the extent of volume change or confirm the output. It could be more complete by indicating whether it increases by a fixed step or continuously.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are no parameters in the input schema, so the description naturally adds no parameter information. According to the guidelines, with 0 parameters the baseline score is 4, which is appropriate as the description does not need to elaborate on parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'turn up the volume' uses a specific verb and resource, clearly indicating that the tool increases the system volume. It unambiguously distinguishes itself from sibling tools like volume_down and volume_mute.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives such as volume_down or volume_mute. It does not mention any prerequisites, exclusions, or context for use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

16 tool updatesv0.1.0Jun 12, 2026
- First observedclick
- First observedcurrent_app
- First observedget_screenshot
- First observedget_uilayout
- First observedinput_text
- First observedlaunch_app
- First observedlist_app
- First observedlong_click
- First observedmedia_next
- First observedmedia_play_pause
- First observedmedia_previous
- First observedstop_app
- First observedswipe
- First observedvolume_down
- First observedvolume_mute
- First observedvolume_up

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3/5.0

Scored 2026-06-12 18:46 across 16 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: UI interaction tools (click, long_click, swipe, input_text, get_screenshot, get_uilayout) are well-separated from app management (launch_app, stop_app, list_app, current_app) and media controls (media_*, volume_*). No two tools have overlapping functionality.

Naming Consistency4/5

Tools follow a predictable pattern: UI tools use verb_noun (e.g., get_screenshot, launch_app) and media/volume tools use noun_verb (e.g., media_next, volume_down). While consistent within subdomains, the two patterns differ slightly, but overall naming is readable and logical.

Tool Count5/5

16 tools is well-scoped for a server covering both UI automation and media control. Each tool serves a clear function without redundancy, and the number is appropriate for the domain.

Completeness4/5

The tool set covers core UI actions (click, input, screenshot, layout) and app lifecycle (launch, stop, list, current), plus media and volume controls. Minor gaps like missing swipe description and common UI actions (e.g., back, scroll) are present, but the set is largely complete for typical tasks.

Maintenance

ActivityInactive

ResponsivenessUnresponsive

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

mytesla.ioOAuth
io.mytesla
Control your Tesla from your AI assistant - climate, charging, access, and security.
Home Automation & IoT Travel & Transportation
2
dittu A
io.github.BorisGujvin
Turns a phone into a camera+Bluetooth remote so AI assistants can see and control any PC.
Image & Video Processing OS Automation
122
OpenClaw Direct AOAuth
direct.openclaw
Deploy, monitor, and manage your OpenClaw AI assistants via natural language.
Agent Orchestration Autonomous Agents Monitoring
2
Subotiz MCP
io.github.Subotiz
Connect AI assistants to Subotiz - Using Subotiz's external capabilities through natural language
Developer Tools App Automation
21

Related MCP Servers

@qirabot/mcp
OS Automation App Automation
qirabot
A
license
A
quality
B
maintenance
Enables AI assistants to control mobile and desktop devices with natural language, including running automation tasks, taking screenshots, and managing devices.
Updated 4 months ago (2026-05-13 16:06 UTC)
6
5 npm
MIT
matter-mcp-server
Home Automation & IoT Embedded system
MatterCoder
A
license
Not graded
quality
D
maintenance
Enables AI assistants to directly interact with Matter devices and protocol operations, including device commissioning, attribute read/write, commands, and event monitoring, through natural language.
Updated a year ago (2025-03-24 13:26 UTC)
7
MIT
Huawei MCP Server
Cloud Platforms Developer Tools
filhocf
A
license
Not graded
quality
F
maintenance
Enables AI assistants to operate Huawei Cloud resources (ECS, OBS, GaussDB, etc.) through conversational workflows via the Model Context Protocol.
Updated 4 months ago (2026-05-11 15:51 UTC)
Apache 2.0
mcp-mijia
Home Automation & IoT
oujiafan
A
license
Not graded
quality
D
maintenance
Enables AI assistants to control Xiaomi Mi Home smart devices through natural language, supporting device listing, property control, actions, and scenes.
Updated 6 months ago (2026-03-10 17:20 UTC)
7
MIT

Appeared in Searches

A search assistant for finding Hisense air conditioners