Skip to main content
Glama
enesjakozh
yorrickjansen

Strava MCP Server

by yorrickjansen
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Strava MCP 服务器

CI/CD 管道 代码验证

用于与 Strava API 交互的模型上下文协议 (MCP) 服务器。

用户指南

安装

您可以使用uvx轻松安装 Strava MCP：

uvx strava-mcp

设置 Strava 凭证

  1. 创建 Strava API 应用程序：

  2. 配置您的凭证：创建凭证文件（例如， ~/.ssh/strava.sh ）：

    export STRAVA_CLIENT_ID=your_client_id
export STRAVA_CLIENT_SECRET=your_client_secret

  3. 配置 Claude 桌面：将以下内容添加到您的 Claude 配置（ /Users/<username>/Library/Application Support/Claude/claude_desktop_config.json ）：

    "strava": {
    "command": "bash",
    "args": [
        "-c",
        "source ~/.ssh/strava.sh && uvx strava-mcp"
    ]
}

验证

首次使用 Strava MCP 工具时：

  1. 身份验证流程将自动启动

  2. 您的浏览器将打开 Strava 授权页面

  3. 授权后，您将被重定向回本地页面

  4. 您的刷新令牌将自动保存以供将来使用

可用工具

获取用户活动

检索经过身份验证的用户的活动。

参数：

  • before （可选）：用于过滤的纪元时间戳

  • after （可选）：用于过滤的纪元时间戳

  • page （可选）：页码（默认值：1）

  • per_page （可选）：每页项目数（默认值：30）

获取活动

获取有关特定活动的详细信息。

参数：

  • activity_id ：活动的 ID

  • include_all_efforts （可选）：包括细分工作（默认值：false）

获取活动片段

从特定活动中检索片段。

参数：

  • activity_id ：活动的 ID

获取细分排行榜

获取特定部分的排行榜。

参数：

  • segment_id ：段的 ID

  • 各种可选过滤器（性别、年龄组等）

Related MCP server: Strava MCP Server

开发者指南

项目设置

  1. 克隆存储库：

    git clone <repository-url>
cd strava

  2. 安装依赖项：

    uv install

  3. 设置环境变量：

    export STRAVA_CLIENT_ID=your_client_id
export STRAVA_CLIENT_SECRET=your_client_secret

    或者，使用这些变量创建一个.env文件。

以开发模式运行

使用 MCP CLI 运行服务器：

mcp dev strava_mcp/main.py

手动身份验证

您可以通过运行以下命令手动获取刷新令牌：

python get_token.py

项目结构

  • strava_mcp/ ：主包目录

    • __init__.py ：包初始化

    • config.py ：使用 pydantic-settings 进行配置设置

    • models.py ：Strava API 实体的 Pydantic 模型

    • api.py的低级 API 客户端

    • auth.py ：Strava OAuth 身份验证实现

    • oauth_server.py ：独立 OAuth 服务器实现

    • service.py ：业务逻辑的服务层

    • server.py ：MCP 服务器实现

  • tests/ ：单元测试

  • strava_mcp/main.py ：运行服务器的主入口点

  • get_token.py ：用于手动获取刷新令牌的实用程序脚本

运行测试

pytest

发布到 PyPI

构建包

# Build both sdist and wheel
uv build

发布到 PyPI

# Publish to Test PyPI first
uv publish --index testpypi

# Publish to PyPI
uv publish

执照

MIT 许可证

致谢

Available Tools

3 tools
get_activityC

Get details of a specific activity.

Args: ctx: The MCP request context activity_id: The ID of the activity include_all_efforts: Whether to include all segment efforts

Returns: The activity details

ParametersJSON Schema
NameRequiredDescriptionDefault
activity_idYes
include_all_effortsNo

TDQS

C2.9/5.0
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 'Get details' but doesn't clarify if this is a read-only operation, what permissions might be required, error handling, or response format beyond 'The activity details.' 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.

Conciseness4/5

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

The description is structured with a clear purpose statement followed by Args and Returns sections, making it easy to parse. It's concise with no wasted words, though the Args section could be more integrated into the main text for better flow.

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 complexity (2 parameters, no output schema, no annotations), the description is incomplete. It lacks details on error cases, authentication needs, rate limits, or what 'activity details' include, which are crucial for proper tool invocation. Without annotations or output schema, the description should provide more context to be fully helpful.

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 minimal semantics beyond the input schema. It explains that 'activity_id' is 'The ID of the activity' and 'include_all_efforts' is 'Whether to include all segment efforts,' which clarifies purpose but doesn't provide format details or examples. With 0% schema description coverage, this partially compensates but remains basic, aligning with the baseline expectation when schema coverage is low.

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 details of a specific activity.' This is a specific verb ('Get') and resource ('activity'), making it understandable. However, it doesn't explicitly differentiate from sibling tools like 'get_activity_segments' or 'get_user_activities', which likely retrieve related but different data.

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 sibling tools like 'get_activity_segments' (which might retrieve parts of an activity) or 'get_user_activities' (which might list multiple activities), leaving the agent to infer usage context without explicit direction.

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

get_activity_segmentsC

Get the segments of a specific activity.

Args: ctx: The MCP request context activity_id: The ID of the activity

Returns: List of segment efforts for the activity

ParametersJSON Schema
NameRequiredDescriptionDefault
activity_idYes

TDQS

C2.9/5.0
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 'Get[s] the segments' and returns a 'List of segment efforts for the activity', which implies a read-only operation, but it doesn't disclose any behavioral traits such as authentication needs, rate limits, error handling, or what 'segment efforts' entail. For a tool with zero annotation coverage, this leaves significant gaps in understanding how it behaves.

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 appropriately sized and front-loaded, with the main purpose stated first ('Get the segments of a specific activity.'). The Args and Returns sections are structured but could be more integrated. It avoids unnecessary fluff, but the separation into sections might slightly reduce flow. Overall, it's efficient with little waste.

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 complexity (a read operation with one parameter) and lack of annotations or output schema, the description is incomplete. It doesn't explain what 'segment efforts' are, how the list is structured, or any behavioral aspects like pagination or errors. For a tool with no structured data support, the description should provide more context to be fully helpful.

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 minimal meaning beyond the input schema. It mentions 'activity_id: The ID of the activity', which is already clear from the schema's title 'Activity Id' and type 'integer'. With 0% schema description coverage, the description doesn't compensate by providing additional context, such as where to find the activity ID or format requirements. However, since there's only one parameter, the baseline is higher, but it still lacks enrichment.

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 the segments of a specific activity.' It uses a specific verb ('Get') and resource ('segments of a specific activity'), making it easy to understand what the tool does. However, it doesn't explicitly distinguish this from sibling tools like 'get_activity' or 'get_user_activities' in terms of what specific data it returns versus those tools.

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 sibling tools like 'get_activity' or 'get_user_activities', nor does it specify prerequisites, exclusions, or contextual cues for choosing this tool over others. The only implied usage is when you need segments for a specific activity, but this is basic and lacks comparative guidance.

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

get_user_activitiesB

Get the authenticated user's activities.

Args: ctx: The MCP request context before: An epoch timestamp for filtering activities before a certain time after: An epoch timestamp for filtering activities after a certain time page: Page number per_page: Number of items per page

Returns: List of activities

ParametersJSON Schema
NameRequiredDescriptionDefault
beforeNo
afterNo
pageNo
per_pageNo

TDQS

B3.2/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions that it returns a 'List of activities' and includes pagination parameters, which hints at a read-only operation. However, it lacks details on authentication requirements, rate limits, error handling, or what constitutes an 'activity' (e.g., format, fields). This leaves significant gaps for an agent to understand the tool's behavior fully.

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 well-structured and appropriately sized. It starts with a clear purpose statement, followed by organized sections for 'Args' and 'Returns'. Each sentence adds value without redundancy, making it easy to parse and understand quickly. There's no wasted verbiage.

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 complexity (4 parameters, no annotations, no output schema), the description is moderately complete. It covers the purpose and parameters but lacks details on authentication, error cases, sibling differentiation, and the structure of returned activities. Without an output schema, the agent must infer the return format from the vague 'List of activities'. This is adequate but has clear gaps for a tool with multiple parameters and siblings.

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 schema description coverage is 0%, but the description compensates by listing all four parameters ('before', 'after', 'page', 'per_page') with brief explanations in the 'Args' section. It clarifies that 'before' and 'after' are epoch timestamps for filtering, and 'page' and 'per_page' handle pagination. This adds meaningful context beyond the bare schema, though it doesn't detail defaults or constraints like valid ranges.

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 the authenticated user's activities.' It specifies the verb ('Get') and resource ('authenticated user's activities'), making it clear what the tool does. However, it doesn't explicitly differentiate from sibling tools like 'get_activity' or 'get_activity_segments', 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 its siblings ('get_activity' and 'get_activity_segments'). It doesn't mention any prerequisites, exclusions, or alternative scenarios. The only implied usage is for retrieving the user's activities, but this is too vague for effective tool selection.

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. 3 tool updates
    • First observedget_activity
    • First observedget_activity_segments
    • First observedget_user_activities
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

B3.1/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: get_activity retrieves details of a specific activity, get_activity_segments focuses on segments within an activity, and get_user_activities lists the user's activities. The descriptions clearly differentiate these functions, making tool selection unambiguous for an agent.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with snake_case (get_activity, get_activity_segments, get_user_activities). The naming is predictable and readable, using 'get' as the verb throughout, which aligns well with the read-only nature of these tools.

Tool Count2/5

With only 3 tools, this server feels under-scoped for a Strava integration, which typically involves activities, segments, athletes, and more. While the tools cover some read operations, the count is too low to support comprehensive agent workflows, such as creating or updating activities, which are common in fitness tracking domains.

Completeness2/5

The tool surface is severely incomplete for a Strava server, as it only includes read operations (get) with no support for create, update, or delete actions. There are significant gaps, such as missing tools for managing segments, athletes, or uploading activities, which will likely cause agent failures when attempting full interactions with the Strava API.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Strava MCP Server

    tomekkorbak
    A
    license
    B
    quality
    D
    maintenance
    A Model Context Protocol server that provides language models with access to Strava API data, allowing them to query and analyze athlete activities from Strava.
    4
    24
    MIT

  • Strava MCP Server

    ctvidic
    A
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol server that enables language models to interact with Strava data, including activities, athlete statistics, routes, achievements, and social features.
    6
    MIT

  • Strava MCP Server

    justmytwospence
    A
    license
    A
    quality
    D
    maintenance
    An MCP server that enables interaction with the Strava API v3 to manage fitness activities, athlete profiles, segments, and routes. It supports retrieving detailed performance metrics, exploring geographic data, and managing club information through natural language.
    110 npm
    ISC

Appeared in Searches