# Tools reference Complete reference of every tool the GroupDocs.Parser MCP server exposes to AI agents, with parameters, example prompts, and results. Complete reference of every tool the GroupDocs.Parser MCP server exposes to AI agents, with parameters, example prompts, and results. Captured from a live `tools/list` call against server version **26.9.0** (raw capture: `tools-list.generated.json` in this section's source). | Tool | What it does | |---|---| | [`extract_text`]({{< ref "parser/mcp/tools-reference/extract-text.md" >}}) | Extracts plain text from a document, whole or a single page | | [`extract_tables`]({{< ref "parser/mcp/tools-reference/extract-tables.md" >}}) | Extracts tables as Markdown (renders in chat) or structured JSON | | [`extract_metadata`]({{< ref "parser/mcp/tools-reference/extract-metadata.md" >}}) | Extracts author, title, dates, custom properties, EXIF, XMP, IPTC as JSON | | [`extract_images`]({{< ref "parser/mcp/tools-reference/extract-images.md" >}}) | Extracts embedded images and saves them to storage as files | | [`extract_barcodes`]({{< ref "parser/mcp/tools-reference/extract-barcodes.md" >}}) | Decodes barcodes and QR codes, returning values, types, pages, confidence and angle | | [`get_document_info`]({{< ref "parser/mcp/tools-reference/get-document-info.md" >}}) | Returns file type, page count, and size without extracting anything | | [`get_license_status`]({{< ref "parser/mcp/tools-reference/get-license-status.md" >}}) | Reports the active licensing mode and, under metered licensing, consumption | ## The FileInput shape Every tool takes its document through the same `file` object — pass **either** a name from your storage folder **or** inline content: ```json { "file": { "filePath": "invoice.pdf" } } ``` | Field | Type | Description | |---|---|---| | `filePath` | string | File path or name in the configured storage folder | | `fileContent` | string | Base64-encoded file content (alternative to `filePath`) | | `fileName` | string | Original filename with extension — required with `fileContent`. It also works on its own, resolved from the storage folder exactly like `filePath` | You rarely write this JSON yourself: the AI agent does, from your plain-language prompt. Missing files are not an error to fear — the tool responds with the list of available files so the agent can correct itself. ## Contents - [extract_text](https://docs.groupdocs.com/parser/mcp/tools-reference/extract-text.md) - [extract_tables](https://docs.groupdocs.com/parser/mcp/tools-reference/extract-tables.md) - [extract_metadata](https://docs.groupdocs.com/parser/mcp/tools-reference/extract-metadata.md) - [extract_images](https://docs.groupdocs.com/parser/mcp/tools-reference/extract-images.md) - [extract_barcodes](https://docs.groupdocs.com/parser/mcp/tools-reference/extract-barcodes.md) - [get_document_info](https://docs.groupdocs.com/parser/mcp/tools-reference/get-document-info.md) - [get_license_status](https://docs.groupdocs.com/parser/mcp/tools-reference/get-license-status.md)