microsoft_clarity-automation by composiohq/awesome-claude-skills
npx skills add https://github.com/composiohq/awesome-claude-skills --skill microsoft_clarity-automation通过 Rube MCP 使用 Composio 的 Microsoft Clarity 工具包自动化 Microsoft Clarity 操作。
工具包文档 : composio.dev/toolkits/microsoft_clarity
RUBE_SEARCH_TOOLS 可用)RUBE_MANAGE_CONNECTIONS 使用工具包 microsoft_clarity 建立活跃的 Microsoft Clarity 连接RUBE_SEARCH_TOOLS 以获取当前工具模式获取 Rube MCP : 在您的客户端配置中将 https://rube.app/mcp 添加为 MCP 服务器。无需 API 密钥——只需添加端点即可工作。
RUBE_SEARCH_TOOLS 有响应来验证 Rube MCP 可用广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
microsoft_clarity 调用 RUBE_MANAGE_CONNECTIONS在执行工作流之前,始终先发现可用工具:
RUBE_SEARCH_TOOLS: queries=[{"use_case": "session recordings, heatmaps, and user behavior analytics", "known_fields": ""}]
这将返回:
RUBE_SEARCH_TOOLS:
queries:
- use_case: "list all available Microsoft Clarity tools and capabilities"
在继续之前,请查看返回的工具、它们的描述和输入模式。
发现工具后,通过以下方式执行它们:
RUBE_MULTI_EXECUTE_TOOL:
tools:
- tool_slug: "<discovered_tool_slug>"
arguments: {<schema-compliant arguments>}
memory: {}
sync_response_to_workbench: false
对于涉及多个 Microsoft Clarity 操作的复杂工作流:
RUBE_SEARCH_TOOLSRUBE_REMOTE_WORKBENCH在创建新资源之前,始终先搜索现有资源,以避免重复。
许多列表操作支持分页。检查响应中的 next_cursor 或 page_token,并在耗尽之前继续获取。
RUBE_MANAGE_CONNECTIONS 重新认证对于批量操作,在循环中使用 RUBE_REMOTE_WORKBENCH 和 run_composio_tool(),并结合 ThreadPoolExecutor 进行并行执行。
RUBE_SEARCH_TOOLS 发现它们的情况下硬编码工具标识符。schemaRef 而不是 input_schema 时,使用 RUBE_GET_TOOL_SCHEMAS 加载完整的输入模式。| 操作 | 方法 |
|---|---|
| 查找工具 | 使用 Microsoft Clarity 特定用例调用 RUBE_SEARCH_TOOLS |
| 连接 | 使用工具包 microsoft_clarity 调用 RUBE_MANAGE_CONNECTIONS |
| 执行 | 使用发现的工具标识符调用 RUBE_MULTI_EXECUTE_TOOL |
| 批量操作 | 使用 run_composio_tool() 调用 RUBE_REMOTE_WORKBENCH |
| 完整模式 | 对于带有 schemaRef 的工具,使用 RUBE_GET_TOOL_SCHEMAS |
每周安装数
1
代码仓库
GitHub 星标数
42.3K
首次出现
2026年2月16日
安装于
mcpjam1
claude-code1
replit1
junie1
windsurf1
zencoder1
Automate Microsoft Clarity operations through Composio's Microsoft Clarity toolkit via Rube MCP.
Toolkit docs : composio.dev/toolkits/microsoft_clarity
RUBE_MANAGE_CONNECTIONS with toolkit microsoft_clarityRUBE_SEARCH_TOOLS first to get current tool schemasGet Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
RUBE_SEARCH_TOOLS respondsRUBE_MANAGE_CONNECTIONS with toolkit microsoft_clarityAlways discover available tools before executing workflows:
RUBE_SEARCH_TOOLS: queries=[{"use_case": "session recordings, heatmaps, and user behavior analytics", "known_fields": ""}]
This returns:
RUBE_SEARCH_TOOLS:
queries:
- use_case: "list all available Microsoft Clarity tools and capabilities"
Review the returned tools, their descriptions, and input schemas before proceeding.
After discovering tools, execute them via:
RUBE_MULTI_EXECUTE_TOOL:
tools:
- tool_slug: "<discovered_tool_slug>"
arguments: {<schema-compliant arguments>}
memory: {}
sync_response_to_workbench: false
For complex workflows involving multiple Microsoft Clarity operations:
RUBE_SEARCH_TOOLS with specific use caseRUBE_REMOTE_WORKBENCH for bulk operations or data processingAlways search for existing resources before creating new ones to avoid duplicates.
Many list operations support pagination. Check responses for next_cursor or page_token and continue fetching until exhausted.
RUBE_MANAGE_CONNECTIONS if connection expiredFor bulk operations, use RUBE_REMOTE_WORKBENCH with run_composio_tool() in a loop with ThreadPoolExecutor for parallel execution.
RUBE_SEARCH_TOOLS.RUBE_GET_TOOL_SCHEMAS to load full input schemas when schemaRef is returned instead of input_schema.| Operation | Approach |
|---|---|
| Find tools | RUBE_SEARCH_TOOLS with Microsoft Clarity-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit microsoft_clarity |
| Execute | RUBE_MULTI_EXECUTE_TOOL with discovered tool slugs |
| Bulk ops | RUBE_REMOTE_WORKBENCH with run_composio_tool() |
| Full schema | RUBE_GET_TOOL_SCHEMAS for tools with |
Toolkit docs : composio.dev/toolkits/microsoft_clarity
Weekly Installs
1
Repository
GitHub Stars
42.3K
First Seen
Feb 16, 2026
Installed on
mcpjam1
claude-code1
replit1
junie1
windsurf1
zencoder1
Python PDF处理教程:合并拆分、提取文本表格、创建PDF文件
58,600 周安装
schemaRef