Skip to main content
Glama
deenesjakoruzh
8bitgentleman

ActivityWatch MCP Server

by 8bitgentleman
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

ActivityWatch MCP 服务器

一个模型上下文协议 (MCP) 服务器，用于连接 ActivityWatch，允许像 Claude 这样的 LLM 与你的时间跟踪数据进行交互。

功能

  • 列出存储桶 (List Buckets)：查看所有可用的 ActivityWatch 存储桶

  • 运行查询 (Run Queries)：执行强大的 AQL (ActivityWatch 查询语言) 查询

  • 获取原始事件 (Get Raw Events)：直接从任何存储桶中检索事件

  • 获取设置 (Get Settings)：访问 ActivityWatch 配置设置

Related MCP server: Paprika SQL MCP Server

安装

你可以通过 npm 安装 ActivityWatch MCP 服务器，也可以自行构建。

通过 npm 安装 (即将推出)

# Global installation
npm install -g activitywatch-mcp-server

# Or install locally
npm install activitywatch-mcp-server

从源码构建

  1. 克隆此仓库：

    git clone https://github.com/8bitgentleman/activitywatch-mcp-server.git
cd activitywatch-mcp-server

  2. 安装依赖：

    npm install

  3. 构建项目：

    npm run build

先决条件

  • 已安装并运行 ActivityWatch

  • Node.js (v14 或更高版本)

  • Claude for Desktop (或任何其他 MCP 客户端)

使用方法

在 Claude for Desktop 中使用

  1. 打开你的 Claude for Desktop 配置文件：

    • Windows: %APPDATA%\Claude\claude_desktop_config.json

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  2. 添加 MCP 服务器配置：

    {
"mcpServers": {
    "activitywatch": {
    "command": "activitywatch-mcp-server",
    "args": []
    }
}
}

    如果你是从源码构建的，请使用：

    {
"mcpServers": {
    "activitywatch": {
    "command": "node",
    "args": ["/path/to/activitywatch-mcp-server/dist/index.js"]
    }
}
}

  3. 重启 Claude for Desktop

  4. 在 Claude 界面中查找 MCP 图标以确认其正在运行

在 Linux 上使用无根 podman 容器配合 Gemini CLI

请确保先使用以下命令构建镜像：

version=$(npm pkg get version | tr -d '"')
podman build . -t activitywatch-mcp-server:${version}

此示例使用了 Activity Watch 在 127.0.0.1 上不可用的覆盖设置（请参阅下一节）。如果不需要，可以省略 AW_API_BASE 环境变量。

{
  "mcpServers": {
    "activitywatch-mcp-server": {
      "command": "/usr/bin/podman",
      "args": [
        "run",
        "--rm",
        "--interactive",
        "--userns=keep-id",
        "-e",
        "AW_API_BASE",
        "localhost/activitywatch-mcp-server:1.2.1"
      ],
      "env": {
        "AW_API_BASE": "http://mydesktop.local:5600/api/0"
      }
    }
  }
}

覆盖 ActivityWatch 服务器主机/端口

如果你想从 Windows Linux 子系统 (WSL) 内部运行此 MCP 服务器（例如在容器内），则在 Windows 上运行的 AW 服务器将无法在 127.0.0.1 上访问。要覆盖标准 localhost 连接，请使用环境变量 AW_API_BASE 或 --aw-api-base 标志，如下所示：

# Using environment variable
export AW_API_BASE=http://mydesktop.local:5600/api/0
node dist/index.js

# Or using command-line flag
node dist/index.js --aw-api-base=http://mydesktop.local:5600/api/0

注意：AW 服务器可能会对用于连接它的名称比较挑剔，但它会接受与运行它的计算机名称匹配并带有 .local 后缀的名称。

查询示例

以下是一些你可以在 Claude 中尝试的查询示例：

  • 列出所有存储桶：“我有哪些 ActivityWatch 存储桶？”

  • 获取应用程序使用摘要：“你能告诉我今天我使用最多的应用程序是什么吗？”

  • 查看浏览历史：“我今天在哪些网站上花费的时间最多？”

  • 检查生产力：“我今天在生产力应用程序上花费了多少时间？”

  • 查看设置：“我的 ActivityWatch 设置是什么？”或“你能检查一下 ActivityWatch 中的特定设置吗？”

可用工具

list-buckets

列出所有可用的 ActivityWatch 存储桶，并支持可选的类型过滤。

参数：

  • type (可选)：按类型过滤存储桶（例如：“window”、“web”、“afk”）

  • includeData (可选)：在响应中包含存储桶数据

run-query

在 ActivityWatch 的查询语言 (AQL) 中运行查询。

参数：

  • timeperiods：要查询的时间段，格式为字符串数组。对于日期范围，请使用格式：["2024-10-28/2024-10-29"]

  • query：ActivityWatch 查询语言中的查询语句数组，其中每一项都是一个完整的查询，语句之间用分号分隔

  • name (可选)：查询名称（用于缓存）

重要提示：每个查询字符串应包含一个完整的查询，其中多个语句用分号分隔。

示例请求格式：

{
  "timeperiods": ["2024-10-28/2024-10-29"],
  "query": ["events = query_bucket('aw-watcher-window_UNI-qUxy6XHnLkk'); RETURN = events;"]
}

请注意：

  • timeperiods 应具有预先格式化的带斜杠的日期范围

  • query 数组中的每一项都是包含所有语句的完整查询

get-events

从 ActivityWatch 存储桶获取原始事件。

参数：

  • bucketId：要从中获取事件的存储桶 ID

  • start (可选)：ISO 格式的开始日期/时间

  • end (可选)：ISO 格式的结束日期/时间

  • limit (可选)：要返回的最大事件数

get-settings

从服务器获取 ActivityWatch 设置。

参数：

  • key (可选)：获取特定的设置键，而不是所有设置

查询语言示例

ActivityWatch 使用一种简单的查询语言。以下是一些常见的模式：

// Get window events
window_events = query_bucket(find_bucket("aw-watcher-window_"));
RETURN = window_events;

// Get only when not AFK
afk_events = query_bucket(find_bucket("aw-watcher-afk_"));
not_afk = filter_keyvals(afk_events, "status", ["not-afk"]);
window_events = filter_period_intersect(window_events, not_afk);
RETURN = window_events;

// Group by app
window_events = query_bucket(find_bucket("aw-watcher-window_"));
events_by_app = merge_events_by_keys(window_events, ["app"]);
RETURN = sort_by_duration(events_by_app);

// Filter by app name
window_events = query_bucket(find_bucket("aw-watcher-window_"));
code_events = filter_keyvals(window_events, "app", ["Code"]);
RETURN = code_events;

配置

服务器默认连接到 http://localhost:5600 的 ActivityWatch API。如果你的 ActivityWatch 实例运行在不同的主机或端口上，你可以按照上述“覆盖 ActivityWatch 服务器主机/端口”部分中的说明进行覆盖。

故障排除

ActivityWatch 未运行

如果 ActivityWatch 未运行，服务器将显示连接错误。请确保 ActivityWatch 正在运行，并且可以在指定的主机/端口地址（除非你已覆盖它，否则为 http://localhost:5600）访问。

查询错误

如果你遇到查询错误：

  1. 检查你的查询语法

  2. 确保存储桶 ID 正确

  3. 验证时间段内包含数据

  4. 查看 ActivityWatch 日志以获取更多详细信息

Claude/MCP 查询格式问题

如果 Claude 在通过此 MCP 服务器运行查询时报告错误，很可能是由于格式问题。请确保你的查询在提示词中遵循此确切格式：

{
  "timeperiods": ["2024-10-28/2024-10-29"],
  "query": ["events = query_bucket('aw-watcher-window_UNI-qUxy6XHnLkk'); RETURN = events;"]
}

常见问题：

  • 时间段格式不正确（应在数组内的单个字符串中为“开始/结束”）

  • 查询语句被拆分为单独的数组元素，而不是组合在一个字符串中

最常见的格式问题

最常见的错误是 Claude 将每个查询语句拆分为自己的数组元素，如下所示：

{
  "query": [
    "browser_events = query_bucket('aw-watcher-web');",
    "afk_events = query_bucket('aw-watcher-afk');",
    "RETURN = events;"
  ],
  "timeperiods": ["2024-10-28/2024-10-29"]
}

这是错误的。相反，所有语句都应位于数组内的单个字符串中：

{
  "timeperiods": ["2024-10-28/2024-10-29"],
  "query": ["browser_events = query_bucket('aw-watcher-web'); afk_events = query_bucket('aw-watcher-afk'); RETURN = events;"]
}

提示 Claude 时

在提示 Claude 时，请明确格式并使用示例。例如，说：

“运行一个查询，其中 timeperiods 为 ["2024-10-28/2024-10-29"]，查询为 ["statement1; statement2; RETURN = result;"]。重要提示：确保所有查询语句都在数组内的单个字符串中，而不是拆分为单独的数组元素。”

贡献

欢迎贡献！请随时提交 Pull Request。

许可证

MIT

Available Tools

5 tools
activitywatch_get_eventsC

Get raw events from an ActivityWatch bucket

ParametersJSON Schema
NameRequiredDescriptionDefault
bucketIdYesID of the bucket to fetch events from
limitNoMaximum number of events to return (default: 100)
startNoStart date/time in ISO format (e.g. '2024-02-01T00:00:00Z')
endNoEnd date/time in ISO format (e.g. '2024-02-28T23:59:59Z')

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure but offers minimal information. It doesn't mention whether this is a read-only operation, if it requires authentication, potential rate limits, error conditions, or what format the 'raw events' are returned in. The description is functionally adequate but lacks important operational context.

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 - a single sentence that communicates the essential purpose without any wasted words. It's front-loaded with the core functionality and doesn't include unnecessary elaboration, making it efficient for quick understanding.

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?

For a tool with 4 parameters, no annotations, and no output schema, the description is insufficiently complete. It doesn't explain what 'raw events' means in terms of data structure, doesn't mention any limitations or constraints, and provides no context about the ActivityWatch system. The agent would need to guess about the return format and operational characteristics.

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?

With 100% schema description coverage, the input schema already documents all 4 parameters thoroughly. The description adds no additional parameter information beyond what's in the schema, so it meets the baseline expectation but doesn't provide extra value regarding parameter usage or semantics.

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 ('Get raw events') and resource ('from an ActivityWatch bucket'), making the purpose immediately understandable. However, it doesn't differentiate this tool from sibling tools like 'activitywatch_query_examples' or 'activitywatch_run_query', which might also retrieve event data but with different approaches or formats.

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. With sibling tools like 'activitywatch_query_examples' and 'activitywatch_run_query' that might serve similar purposes, there's no indication of when this raw event retrieval is preferred over those query-based approaches, leaving the agent without context for selection.

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

activitywatch_get_settingsB

Get ActivityWatch settings. Can retrieve all settings or a specific key if provided.

ParametersJSON Schema
NameRequiredDescriptionDefault
keyNoOptional: Get a specific settings key instead of all settings

TDQS

B3.2/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden. It states the tool retrieves settings but doesn't disclose behavioral traits such as whether it's read-only (implied by 'Get'), authentication needs, rate limits, error handling, or response format. The description is minimal and lacks necessary context for safe and effective use.

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 appropriately sized with two concise sentences that are front-loaded and waste-free. It efficiently communicates the core functionality and parameter usage without unnecessary details.

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 no annotations, no output schema, and a simple input schema, the description is incomplete. It doesn't explain what settings are returned, their structure, or any behavioral aspects like permissions or errors. For a tool with zero annotation coverage, more context is needed for adequate agent understanding.

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?

Schema description coverage is 100%, so the schema already documents the optional 'key' parameter. The description adds marginal value by mentioning 'a specific key if provided,' but doesn't provide additional semantics like key examples, format, or constraints beyond what the schema states.

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 tool's purpose with a specific verb ('Get') and resource ('ActivityWatch settings'), and distinguishes between retrieving all settings or a specific key. However, it doesn't explicitly differentiate from sibling tools like 'activitywatch_get_events' or 'activitywatch_list_buckets' beyond the resource name.

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 implies usage by mentioning 'all settings or a specific key if provided,' which suggests when to use the optional parameter. However, it lacks explicit guidance on when to choose this tool over siblings (e.g., vs. 'activitywatch_get_events') or any prerequisites or exclusions.

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

activitywatch_list_bucketsB

List all ActivityWatch buckets with optional type filtering

ParametersJSON Schema
NameRequiredDescriptionDefault
typeNoFilter buckets by type
includeDataNoInclude bucket data in response

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 the full burden of behavioral disclosure. It states it's a list operation with optional filtering, implying it's likely read-only and non-destructive, but doesn't confirm this or address other behavioral aspects like permissions needed, rate limits, pagination, error handling, or what 'includeData' entails. For a tool with no annotation coverage, this leaves significant gaps in understanding its behavior.

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 a single, efficient sentence that front-loads the core purpose ('List all ActivityWatch buckets') and adds a concise modifier ('with optional type filtering'). There is no wasted verbiage, repetition, or unnecessary elaboration, making it easy to parse and understand quickly.

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 moderate complexity (2 parameters, no output schema, no annotations), the description is adequate but incomplete. It covers the basic action and hints at filtering, but lacks details on behavioral traits, usage context, or output expectations. Without annotations or output schema, the agent must infer behavior from the description alone, which is insufficient for confident tool selection in varied scenarios.

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?

Schema description coverage is 100%, so the schema already documents both parameters ('type' for filtering and 'includeData' for including bucket data). The description adds minimal value by mentioning 'optional type filtering,' which aligns with the schema but doesn't provide additional context like example types or implications of including data. With high schema coverage, the baseline is 3, and the description doesn't significantly enhance parameter understanding beyond what's structured.

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 ('List all ActivityWatch buckets') and resource ('ActivityWatch buckets'), making the purpose immediately understandable. It distinguishes itself from siblings like 'activitywatch_get_events' by focusing on buckets rather than events, though it doesn't explicitly contrast with other bucket-related tools (none exist in the sibling list). The optional filtering aspect adds specificity beyond a basic list operation.

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. It mentions optional type filtering but doesn't explain scenarios where filtering is beneficial or when to choose this over other tools like 'activitywatch_query_examples' or 'activitywatch_run_query' for bucket-related tasks. There are no prerequisites, exclusions, or contextual recommendations provided.

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

activitywatch_query_examplesB

Get examples of properly formatted queries for the ActivityWatch MCP server

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.2/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool 'gets examples,' implying a read-only operation, but doesn't clarify if this requires authentication, has rate limits, returns structured data, or involves any side effects. For a tool with zero annotation coverage, this leaves significant gaps in understanding its behavior and constraints.

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 a single, clear sentence: 'Get examples of properly formatted queries for the ActivityWatch MCP server.' It is front-loaded with the core action ('Get examples') and specifies the context ('for the ActivityWatch MCP server'), with zero wasted words. This makes it highly efficient and easy for an agent to parse.

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 (0 parameters, no output schema, no annotations), the description is adequate but has gaps. It explains what the tool does but lacks behavioral details (e.g., response format, authentication needs) and usage guidelines relative to siblings. Without an output schema, it doesn't describe return values, which could hinder an agent's understanding of how to use the examples provided.

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 0 parameters, and the input schema has 100% description coverage (though empty). The description doesn't need to explain parameters, as there are none. It appropriately focuses on the tool's purpose without redundant parameter details, earning a high baseline score for parameter semantics in this context.

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 tool's purpose: 'Get examples of properly formatted queries for the ActivityWatch MCP server.' It uses a specific verb ('Get') and identifies the resource ('examples of properly formatted queries'), making the function unambiguous. However, it doesn't explicitly differentiate from sibling tools like 'activitywatch_run_query' or 'activitywatch_get_events,' which prevents 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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing to understand query syntax before using 'activitywatch_run_query'), exclusions, or contextual cues. Without such information, an agent might struggle to choose between this and sibling tools like 'activitywatch_run_query' or 'activitywatch_get_events.'

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

activitywatch_run_queryC

Run a query in ActivityWatch's query language

ParametersJSON Schema
NameRequiredDescriptionDefault
timeperiodsYesTime periods to query. Format: ['2024-10-28/2024-10-29'] where dates are in ISO format and joined with a slash
queryYesMUST BE A SINGLE STRING containing all query statements separated by semicolons. DO NOT split into multiple strings.
nameNoOptional name for the query (used for caching)

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure but only states the basic action. It doesn't mention whether this is a read-only operation, if it requires specific permissions, potential side effects, rate limits, or what the output looks like (especially critical since there's no output schema). This leaves significant gaps for a query execution tool.

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 a single, efficient sentence that states the core purpose without any wasted words. It's appropriately sized for a tool with well-documented parameters and gets straight to the point, making it easy for an agent to parse quickly.

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?

For a query execution tool with no annotations and no output schema, the description is insufficient. It doesn't explain what kind of results to expect, error conditions, or behavioral constraints. Given the complexity of running queries and the lack of structured output documentation, more context about the operation's nature and results is needed.

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 description adds no parameter information beyond what's already in the schema (which has 100% coverage). While the schema thoroughly documents all three parameters with formats, constraints, and examples, the description doesn't provide additional context about parameter relationships or usage semantics, meeting the baseline for high schema coverage.

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 ('Run a query') and the resource ('in ActivityWatch's query language'), which is specific and unambiguous. However, it doesn't explicitly differentiate this tool from its sibling 'activitywatch_query_examples', which might cause confusion about when to use each.

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 like 'activitywatch_get_events' or 'activitywatch_query_examples'. There's no mention of prerequisites, appropriate contexts, or exclusions, leaving the agent to infer usage from the tool name alone.

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.

  1. 5 tool updatesv1.0.0
    • Addedactivitywatch_get_events
    • Addedactivitywatch_get_settings
    • Addedactivitywatch_list_buckets
    • Addedactivitywatch_query_examples
    • Addedactivitywatch_run_query
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

A3.5/5.0

Scored across 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: get_events retrieves raw event data, get_settings accesses configuration, list_buckets enumerates available data containers, query_examples provides documentation, and run_query executes queries. There is no overlap in functionality that would cause agent confusion.

Naming Consistency5/5

All tools follow a consistent 'activitywatch_verb_noun' pattern with snake_case throughout. The verbs (get, list, run) are appropriately descriptive and maintain a uniform naming convention across all five tools.

Tool Count5/5

With 5 tools, this server is well-scoped for interacting with ActivityWatch data. The count is appropriate for the domain, covering core operations like data retrieval, configuration access, and query execution without being overwhelming or insufficient.

Completeness4/5

The toolset provides solid coverage for querying and inspecting ActivityWatch data, including examples for guidance. A minor gap exists in write operations (e.g., creating or modifying buckets/events), but the available tools support most common read and query workflows effectively.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • TripleWhale MCP Server by Triple-Whale

    TripleWhale MCP Serverofficial

    Triple-Whale
    A
    license
    Not graded
    quality
    C
    maintenance
    An implementation of Model Context Protocol (MCP) that allows users to interact with TripleWhale's e-commerce analytics platform using natural language queries through Claude Desktop.
    106 npm
    7
    MIT

  • Paprika SQL MCP Server

    jonaheaton
    F
    license
    Not graded
    quality
    F
    maintenance
    A Model Context Protocol desktop extension that allows Claude to query and interact with custom SQL databases in real-time during conversations.
    1
    -

  • ActivityWatch MCP Server

    Auriora
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables LLM agents to query and analyze ActivityWatch time tracking data, including window activity, web browsing, and category management with natural language time periods and automatic data aggregation.
    12
    GPL 3.0

  • ActivityWatch MCP Server

    JM-404
    F
    license
    Not graded
    quality
    F
    maintenance
    Connects AI assistants to ActivityWatch for real-time computer activity awareness and time tracking analysis. Enables natural language queries about app usage, browsing history, and productivity patterns through high-level tools without requiring AQL syntax knowledge.
    -

Appeared in Searches