ocr-web-service-automation

自动化调用 OCR 网页服务，批量识别图片或文档中的文字并返回结构化结果

来源

GitHub

更新于

2026-06-07

// 安全评估低风险

仅提示词，不执行代码
开源可审计

正在进行安全审计…

凭证密钥
网络外发
代码执行
数据访问
来源供应链

// 安装

复制安装指令，让 AI 自动完成配置 · 推荐新手

请帮我安装 askskill 上的 "ocr-web-service-automation" 技能：
1. 下载 https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/ocr-web-service-automation/SKILL.md
2. 保存为 ~/.claude/skills/ocr-web-service-automation/SKILL.md
3. 装好后重载技能，告诉我可以用了

// 下载

下载 SKILL.md机读安装清单 ↗

// 用法示例

批量识别发票图片

输入

请先搜索可用工具和当前 schema，然后调用 OCR Web Service，批量处理我提供的发票图片链接，提取发票号、日期、金额、税额和销售方名称，并整理成 JSON 数组返回。

预期产出

返回包含每张发票关键字段的结构化 JSON 结果，便于后续入账或分析。

提取扫描 PDF 文本

输入

请先搜索可用工具和当前 schema，再调用 OCR Web Service 处理这个扫描版 PDF 文件，按页提取正文文字，并输出带页码的纯文本结果。

预期产出

返回按页组织的文本内容，适合复制、检索或进一步摘要。

识别表单并生成字段

输入

请先搜索可用工具和当前 schema，然后调用 OCR Web Service 识别这张表单图片，提取姓名、电话、邮箱、地址和备注等字段；如果字段缺失，请标记为空。

预期产出

返回标准化字段对象，方便导入 CRM、表格或数据库。

// 文档

OCR Web Service Automation via Rube MCP

Automate OCR Web Service operations through Composio's OCR Web Service toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/ocr_web_service

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active OCR Web Service connection via RUBE_MANAGE_CONNECTIONS with toolkit ocr_web_service
Always call RUBE_SEARCH_TOOLS first to get current tool schemas

Setup

Get 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.

Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
Call RUBE_MANAGE_CONNECTIONS with toolkit ocr_web_service
If connection is not ACTIVE, follow the returned auth link to complete setup
Confirm connection status shows ACTIVE before running any workflows

Tool Discovery

Always discover available tools before executing workflows:

RUBE_SEARCH_TOOLS
queries: [{use_case: "OCR Web Service operations", known_fields: ""}]
session: {generate_id: true}

This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.

Core Workflow Pattern

Step 1: Discover Available Tools

RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific OCR Web Service task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["ocr_web_service"]
session_id: "your_session_id"

Step 3: Execute Tools

RUBE_MULTI_EXECUTE_TOOL
tools: [{
  tool_slug: "TOOL_SLUG_FROM_SEARCH",
  arguments: {/* schema-compliant args from search results */}
}]
memory: {}
session_id: "your_session_id"

Known Pitfalls

Always search first: Tool schemas change. Never hardcode tool slugs or arguments without calling RUBE_SEARCH_TOOLS
Check connection: Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing tools
Schema compliance: Use exact field names and types from the search results
Memory parameter: Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Session reuse: Reuse session IDs within a workflow. Generate new ones for new workflows
Pagination: Check responses for pagination tokens and continue fetching until complete

Quick Reference

Operation	Approach
Find tools	`RUBE_SEARCH_TOOLS` with OCR Web Service-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `ocr_web_service`
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 `schemaRef`