Introduction
CamScanner Agent document capabilities provide foundational document processing for agents, IDEs, scripts, and automated workflows. Through Skill, MCP, or CLI, an existing agent can use CamScanner technology to turn source files into usable results.
This is not a new agent platform and does not replace the agent you already use. The agent understands requests, plans steps, and coordinates tasks; CamScanner performs the document-processing operations.
1. Core capabilities
- Scan and image enhancement: handle shadows, blur, dot patterns, moiré, and handwriting, and support image upscaling and old-photo restoration.
- Text recognition: extract plain text, mathematical formulas, or structured invoice and receipt fields from images.
- Format conversion: convert images, PDFs, or TXT into currently supported office documents, text, PDF, or image formats.
- Batch processing: merge up to 100 images in a confirmed order into PDF, Word, Excel, or continuous text.
- Translation and editing: translate and edit image content while preserving the original structure and layout as much as possible.
- Watermarks and authenticity detection: add or remove watermarks from images and PDFs, and detect image tampering and AI-generation risks.
- Cloud saving and document management: save results and search, download, move, and organize cloud documents.
See Supported capabilities for the complete confirmed scope.
2. How it participates in a task
When a user asks an agent to process a document, a typical flow is:
- The user states the goal, for example, “Extract the text from this scanned contract and convert it to an editable document.”
- The agent understands and plans, selecting the required capabilities and their order.
- CamScanner executes the recognition, enhancement, conversion, or other document operation through Skill, MCP, or CLI.
- The agent completes delivery, using the result for summarization, archiving, or the next business step.
You do not need to move to a new work platform or rebuild an entire document pipeline. Choose an integration method in your existing environment and add document capabilities to the current workflow.
3. Use cases
- Agents processing user files: let a user-facing agent understand and process images, scans, or PDFs instead of only suggesting steps.
- Office automation: connect recognition, conversion, merging, and translation to repeatable workflows.
- Development and debugging: invoke capabilities directly from an IDE or local terminal to verify parameters and results.
- Product integration: add professional document capabilities to an existing application while your product owns the interaction.
4. Working with an agent platform
| Component | Primary responsibility |
|---|---|
| Agent platform | Interact with users, understand goals, manage context, and plan and orchestrate tasks |
| CamScanner Agent document capabilities | Receive calls and perform scanning, recognition, conversion, editing, and management operations |
| Your business system | Provide files, permissions, and business rules, and consume the final results |
These components can be combined as needed. CamScanner can serve as the document capability layer for a general agent, a vertical agent, an AI IDE, or a custom automated workflow.
5. Choose an integration method
| Method | Best suited for… |
|---|---|
| Skill | An agent that supports Skills and should understand capability guidance and compose calls automatically |
| MCP | An agent, AI IDE, or workflow that needs standardized tools the model can call as needed |
| CLI | Scripts, batch processing, local development and debugging, or CI workflows |
If you are unsure which to choose, open Connect Agents for an overview of all three methods.
6. Recommended reading order
- Supported capabilities: confirm that the required document task is supported.
- Connect Agents: choose an integration method for your agent or development environment.
- Changelog: review new capabilities, documentation changes, and compatibility updates.