com.mcparmory/pdfco
OCI · GHCR.IO/MCPARMORY/PDFCO:1.0.2 · 2 COMPONENTS · SCANNED SEP 20
Extract data, edit, convert, and parse PDF documents with OCR and AI
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security0
- Malware scan not yet available for this package.Unverified
- Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 130 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability67
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 12004 tokens (~184/item across 65 items; 65 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management80
- Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety89
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 4 of 7 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "merge_pdfs" implies "merge" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Partial
- An AI judge read all 65 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
How do I install the com.mcparmory/pdfco MCP server?
com.mcparmory/pdfco runs locally as a container image, launched with docker run --rm -i ghcr.io/mcparmory/pdfco:1.0.2. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/mcparmory/pdfco:1.0.2
claude mcp add com-mcparmory-pdfco -- docker run --rm -i ghcr.io/mcparmory/pdfco:1.0.2
{
"mcpServers": {
"com-mcparmory-pdfco": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/pdfco:1.0.2"
]
}
}
} {
"servers": {
"com-mcparmory-pdfco": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/pdfco:1.0.2"
]
}
}
} codex mcp add com-mcparmory-pdfco -- docker run --rm -i ghcr.io/mcparmory/pdfco:1.0.2
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"com-mcparmory-pdfco": {
"type": "local",
"command": [
"docker",
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/pdfco:1.0.2"
],
"enabled": true
}
}
} mcp_servers:
com-mcparmory-pdfco:
command: "docker"
args: ["run", "--rm", "-i", "ghcr.io/mcparmory/pdfco:1.0.2"] {
"McpServers": {
"com-mcparmory-pdfco": {
"Transport": "stdio",
"Command": "docker",
"Arguments": [
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/pdfco:1.0.2"
]
}
}
} {
"mcpServers": {
"com-mcparmory-pdfco": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/pdfco:1.0.2"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Sept 26 −3
- Stability: pass → 0.80 functional
- 19 Sept 26 +1
- Stability: 0.97 → pass security
- 17 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 −3
- Stability: pass → 0.77 functional
- 11 Sept 26 +1
- Stability: 0.97 → pass security
- 9 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 7 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed oci/ghcr.io/mcparmory/pdfco:1.0.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
add_content_to_pdf Add Content to PDF ~246
Add or modify content in a PDF document by inserting text annotations, images, other PDFs, and filling form fields. Supports both native PDFs and scanned documents.
| Name | Type | Req | Description |
|---|---|---|---|
| annotationsString | string | yes | One or more text annotations to add to the PDF. Each annotation is semicolon-delimited with parameters: x-coordinate, y-coordinate, page numbers, text content, font size, font name, font color, optio… |
| fieldsString | string | – | Values to populate in fillable PDF form fields. Each entry is semicolon-delimited with parameters: page number, field name, and field value. |
| imagesString | string | – | One or more images or PDF objects to overlay on the source PDF. Each item is semicolon-delimited with parameters: x-coordinate, y-coordinate, page numbers, URL to the image or PDF file, optional link… |
| name | string | – | Name for the output document. Defaults to 'newDocument' if not specified. |
| url | string | yes | URL of the source PDF file to edit. Defaults to a sample PDF if not provided. |
No output schema declared.
No examples provided.
add_password_to_pdf Add Password to PDF ~345
Secure a PDF document by adding password protection and configurable access restrictions. Specify owner and user passwords along with granular permissions for printing, editing, copying, and other document operations.
| Name | Type | Req | Description |
|---|---|---|---|
| allowaccessibilitysupport | boolean | – | Whether to allow screen readers and accessibility tools to access the document content. |
| allowassemblydocument | boolean | – | Whether to allow users to assemble or reorganize pages within the document. |
| allowcontentextraction | boolean | – | Whether to allow users to copy or extract text and graphics from the document. Disabled by default. |
| allowfillforms | boolean | – | Whether to allow users to fill in form fields within the document. Disabled by default. |
| allowmodifyannotations | boolean | – | Whether to allow users to add, modify, or delete annotations and comments. Disabled by default. |
| allowmodifydocument | boolean | – | Whether to allow users to modify or edit the document content. Disabled by default. |
| allowprintdocument | boolean | – | Whether to allow users to print the document. Disabled by default. |
| name | string | – | Output filename for the secured PDF document. Defaults to 'output-protected.pdf' if not specified. |
| ownerpassword | string | – | Password required to modify document permissions and security settings. Defaults to '12345' if not specified. |
| printquality | string | – | Quality level for printing permissions. Set to 'LowResolution' by default to restrict print quality. |
| url | string | yes | URL of the PDF file to secure. Defaults to a sample PDF if not provided. |
| userpassword | string | – | Password required for users to open and view the PDF document. Defaults to '54321' if not specified. |
No output schema declared.
No examples provided.
auto_rotate_pdf_pages Auto Rotate PDF Pages ~149
Automatically corrects the rotation of pages in a scanned PDF using AI-powered text analysis. Supports multiple languages for accurate text detection and orientation correction.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | Language(s) for text recognition during rotation analysis. Use a 3-letter language code (e.g., 'eng' for English). Combine multiple languages with a plus sign (e.g., 'eng+deu') for simultaneous multi… |
| name | string | – | Output filename for the rotated PDF. Specify the desired name with .pdf extension for the returned document. |
| url | string | yes | URL of the PDF file to auto-rotate. Accepts a publicly accessible PDF document URL. |
No output schema declared.
No examples provided.
classify_document Classify Document ~103
Analyzes the content of a PDF, JPG, or PNG document to automatically determine its classification using built-in AI or custom-defined classification rules.
| Name | Type | Req | Description |
|---|---|---|---|
| casesensitive | boolean | – | Controls whether the classification search is case-sensitive. Set to false to ignore case differences during analysis; defaults to true for case-sensitive matching. |
| url | string | yes | URL of the document to classify. Accepts PDF, JPG, or PNG files. Defaults to a sample invoice if not provided. |
No output schema declared.
No examples provided.
compress_pdf Compress PDF ~152
Compress PDF files to reduce their size by optimizing images and content. Supports configurable downsampling, compression formats, and quality settings for color, grayscale, and monochrome images.
| Name | Type | Req | Description |
|---|---|---|---|
| config | object | – | Compression configuration object controlling image optimization strategies. Allows separate settings for color, grayscale, and monochrome images, including downsampling thresholds (in DPI), compressi… |
| name | string | – | Optional file name for the compressed output PDF. If not specified, a default name will be generated. |
| url | string | yes | URL of the PDF file to compress. Defaults to a sample PDF if not provided. |
No output schema declared.
No examples provided.
convert_email_to_pdf Convert Email to PDF ~264
Convert email files (.msg or .eml format) to PDF documents, automatically extracting and embedding any attachments as PDF attachments within the output file.
| Name | Type | Req | Description |
|---|---|---|---|
| footer | string | – | Custom HTML content to display in the footer of every page. Provide valid HTML markup. |
| header | string | – | Custom HTML content to display in the header of every page. Provide valid HTML markup. |
| margins | string | – | Custom page margins as space-separated values (top right bottom left). Supports px, mm, cm, or in units. A single value applies to all sides. Overrides default CSS margins. |
| name | string | – | Output filename for the generated PDF document. Defaults to 'email-with-attachments' if not specified. |
| orientation | string | – | Page orientation for the output PDF: Portrait for vertical layout or Landscape for horizontal layout. Defaults to Portrait. |
| papersize | string | – | Paper size for the output PDF. Use standard sizes (Letter, Legal, A0–A6, etc.) or specify custom dimensions as width and height with optional units (px, mm, cm, or in). |
| url | string | yes | URL pointing to the email file (.msg or .eml) to convert. Defaults to a sample email file if not specified. |
No output schema declared.
No examples provided.
convert_pdf_from_csv Convert PDF from CSV ~95
Convert CSV, XLS, or XLSX spreadsheet files into PDF format. Accepts a file URL and returns a generated PDF document.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Output filename for the generated PDF document. Defaults to 'result.pdf' if not specified. |
| url | string | yes | URL of the CSV, XLS, or XLSX file to convert. Must be a publicly accessible HTTP(S) URL pointing to the spreadsheet file. |
No output schema declared.
No examples provided.
convert_pdf_from_doc Convert PDF From Doc ~109
Convert document files (DOC, DOCX, RTF, TXT, XPS) to PDF format. Accepts a URL pointing to the source document and returns the converted PDF.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Optional filename for the output PDF file. Defaults to 'result.pdf' if not specified. |
| url | string | yes | URL of the source document file to convert. Must point to a valid DOC, DOCX, RTF, TXT, or XPS file accessible via HTTP(S). |
No output schema declared.
No examples provided.
convert_pdf_from_html Convert PDF from HTML ~349
Convert HTML content into a PDF document. The converter processes JavaScript triggered during page load and includes dynamic content like popups in the output.
| Name | Type | Req | Description |
|---|---|---|---|
| donotwaitfullload | boolean | – | When true, speeds up conversion by waiting only for minimal page load instead of full page load completion. Defaults to false for thorough rendering. |
| footer | string | – | Custom HTML content to display in the footer of every page. Must be valid HTML format. |
| header | string | – | Custom HTML content to display in the header of every page. Must be valid HTML format. |
| html | string | yes | The HTML code to convert to PDF. Can include inline styles, scripts, and other HTML elements. |
| margins | string | – | Page margins specified as top, right, bottom, and left values in pixels. Defaults to 40px top/bottom and 20px left/right. |
| mediatype | string | – | Media type used for rendering, typically 'print' for print-optimized output or 'screen' for screen-optimized output. Defaults to print. |
| name | string | – | Output filename for the generated PDF document. Defaults to 'multipagedInvoiceWithQRCode.pdf'. |
| orientation | string | – | Page orientation for the output PDF. Defaults to Portrait; can be set to Landscape for wider layouts. |
| papersize | – | – | Paper size for the output PDF (e.g., Letter, A4, Legal). Defaults to Letter size. |
| printbackground | boolean | – | Whether to print background colors and images in the PDF. Enabled by default. |
| templateid | integer | yes | Template identifier that determines the PDF layout and styling template to apply. Defaults to template 1. |
No output schema declared.
No examples provided.
convert_pdf_from_image Convert PDF from Image ~94
Convert image files (JPG, PNG, TIFF) into PDF format. Accepts one or more image URLs and generates a single PDF document.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Optional custom file name for the generated PDF output file. |
| url | string | yes | One or more image URLs to convert into PDF, separated by commas. Supported formats are JPG, PNG, and TIFF. Images are processed in the order provided. |
No output schema declared.
No examples provided.
convert_pdf_from_url Convert PDF From URL ~297
Convert a webpage from a URL into a PDF document. The converter processes all JavaScript triggered during page load, including dynamic content and popups, with no option to disable scripting.
| Name | Type | Req | Description |
|---|---|---|---|
| donotwaitfullload | boolean | – | When true, speeds up conversion by waiting only for minimal page loading instead of full page load completion. Defaults to false for thorough rendering. |
| footer | string | – | Custom HTML content to display at the bottom of every page in the PDF. Must be valid HTML format. |
| header | string | – | Custom HTML content to display at the top of every page in the PDF. Must be valid HTML format. |
| margins | string | – | Space around the page edges in the PDF output. Specified as a measurement value (e.g., millimeters). Defaults to 5mm. |
| mediatype | string | – | The rendering mode for the conversion. Defaults to print mode for optimal PDF formatting. |
| name | string | – | The filename for the generated PDF file output. |
| orientation | string | – | The page orientation for the PDF output. Defaults to Portrait orientation. |
| papersize | – | – | The paper size for the PDF document. Defaults to Letter size. |
| printbackground | boolean | – | Whether to include background colors and images in the PDF. Enabled by default. |
| url | string | yes | The URL of the webpage to convert to PDF. Defaults to the Wikipedia contact page if not specified. |
No output schema declared.
No examples provided.
convert_pdf_to_csv Convert PDF to CSV ~337
Convert PDF documents and scanned images into CSV format, preserving table structure, columns, rows, and layout information. Supports selective page extraction and configurable text grouping strategies.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | Language code for OCR processing of scanned images. Uses standard language codes (e.g., 'eng' for English). Defaults to English. |
| linegrouping | string | – | Controls how text lines are grouped within table cells during extraction. Choose from three modes (1, 2, or 3) to adjust grouping behavior. See documentation for detailed mode descriptions. |
| name | string | – | Output filename for the generated CSV file. Defaults to 'result.csv'. |
| pages | string | – | Specifies which pages to process using 0-based indices. Supports individual pages (e.g., 0, 5), ranges (e.g., 3-7), open-ended ranges (e.g., 10-), and reverse indexing from the end (!0 for last page)… |
| rect | string | – | Rectangular region to extract from the PDF, specified as four space-separated values: x-coordinate, y-coordinate, width, and height. Use the PDF Edit Add Helper tool to measure coordinates. Only cont… |
| unwrap | boolean | – | When enabled, unwraps multi-line text within table cells into single lines. Only applies when line grouping mode is set to 1. |
| url | string | yes | URL of the PDF file to convert. Can be a direct file URL or a cloud storage link. Defaults to a sample PDF if not provided. |
No output schema declared.
No examples provided.
convert_pdf_to_html Convert PDF to HTML ~305
Convert PDF documents and scanned images into HTML format while preserving text, fonts, images, vectors, and formatting. Supports OCR for scanned documents and selective page/region extraction.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | Language code for OCR processing when converting scanned PDFs or image files. Use three-letter ISO 639-2 language codes (e.g., 'eng' for English). Combine multiple languages with '+' to enable simult… |
| name | string | – | Custom filename for the generated HTML output file. |
| pages | string | – | Page selection using zero-based indices and ranges. Specify individual pages (e.g., '0,2,5'), ranges (e.g., '3-7'), open-ended ranges (e.g., '10-'), or reverse indices from the end (e.g., '!0' for la… |
| rect | string | – | Rectangular region to extract, specified as four space-separated coordinates: x, y, width, and height. Use the PDF Edit Add Helper tool to measure coordinates. Only content within this region will be… |
| url | string | yes | URL of the PDF file to convert. Accepts publicly accessible URLs pointing to PDF documents or scanned images (PNG, JPG). |
No output schema declared.
No examples provided.
convert_pdf_to_jpg Convert PDF to JPG ~225
Convert a PDF document to high-quality JPEG images. Optionally extract specific pages or regions from the PDF.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Output filename for the converted JPEG image. Defaults to 'result.jpg'. |
| pages | string | – | Optional comma-separated list of pages to convert (0-based indexing). Supports individual pages (e.g., '0,2,5'), ranges (e.g., '3-7'), open-ended ranges (e.g., '10-'), and reverse indexing where !0 i… |
| rect | string | – | Optional rectangular region to extract from each page, specified as four space-separated values: x-coordinate, y-coordinate, width, and height (e.g., '10 20 300 400'). If omitted, the entire page is… |
| url | string | yes | URL of the PDF file to convert. Can be a remote URL or a local file path. Defaults to a sample encrypted PDF for testing. |
No output schema declared.
No examples provided.
convert_pdf_to_json Convert PDF to JSON ~369
Convert PDF documents and scanned images into structured JSON format, preserving text content, fonts, images, vectors, and formatting information. Supports OCR for scanned documents and flexible page selection.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | Language code for OCR processing when extracting text from scanned PDFs, PNGs, and JPGs. Use ISO 639-3 three-letter language codes (e.g., 'eng' for English). Combine multiple languages with a plus si… |
| linegrouping | string | – | Controls how text lines are grouped during extraction. Choose from three modes (1, 2, or 3) to adjust line grouping behavior within table cells. Refer to line grouping options documentation for detai… |
| name | string | – | Custom filename for the generated JSON output file. |
| pages | string | – | Specifies which pages to process using zero-based indices and ranges. Supports individual pages (e.g., '0'), ranges (e.g., '3-7'), open-ended ranges (e.g., '10-'), and reverse indexing from the end (… |
| rect | string | – | Rectangular region to extract from the PDF, specified as coordinates in the format: x-position, y-position, width, and height. Use the PDF Edit Add Helper tool to determine precise coordinates for ta… |
| unwrap | boolean | – | When enabled, unwraps multi-line text within table cells into single lines. Only applies when line grouping mode is set to 1. |
| url | string | yes | URL of the PDF file to convert. Accepts publicly accessible URLs pointing to PDF documents or scanned images. |
No output schema declared.
No examples provided.
convert_pdf_to_json_with_ai Convert PDF to JSON with AI ~356
Convert PDF documents and scanned images into structured JSON format using AI-powered extraction. Supports OCR for scanned content, coordinate-based region extraction, and configurable text grouping strategies.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | OCR language code for extracting text from scanned PDFs and images. Use 3-letter ISO 639-2 language codes (e.g., 'eng' for English). Combine multiple languages with '+' to process bilingual documents… |
| linegrouping | string | – | Controls text line grouping strategy during extraction. Mode 1 groups lines tightly, mode 2 uses standard grouping, and mode 3 applies loose grouping. Affects how text is organized in the JSON output. |
| name | string | – | Custom filename for the generated JSON output file. |
| pages | string | – | Specifies which pages to process using 0-based indices. Supports individual pages (e.g., '0,2,5'), ranges (e.g., '3-7'), open-ended ranges (e.g., '10-'), and reverse indexing from the end (e.g., '!0'… |
| rect | string | – | Rectangular region coordinates for targeted extraction. Specify as four space-separated values: x-offset, y-offset, width, and height. Use the PDF Edit Add Helper tool to measure coordinates precisel… |
| unwrap | boolean | – | When enabled with line grouping mode 1, merges multi-line text within table cells into single lines for cleaner output. |
| url | string | yes | URL of the PDF, PNG, or JPG file to convert. Accepts publicly accessible URLs or file paths from supported cloud storage. |
No output schema declared.
No examples provided.
convert_pdf_to_png Convert PDF to PNG ~209
Convert a PDF document to high-quality PNG images. Optionally extract specific regions or pages from the PDF.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Optional custom file name for the generated PNG output file. |
| pages | string | – | Optional page selection using 0-based indices and ranges. Specify individual pages (e.g., '0,2,5'), ranges (e.g., '3-7'), open-ended ranges (e.g., '10-'), or reverse indices from the end (e.g., '!0'… |
| rect | string | – | Optional rectangular region to extract from the PDF, specified as four space-separated values: x-coordinate, y-coordinate, width, and height (e.g., '10 20 300 400'). |
| url | string | yes | URL of the PDF file to convert. Defaults to a sample PDF if not provided. |
No output schema declared.
No examples provided.
convert_pdf_to_text Convert PDF to Text ~366
Convert PDF documents and scanned images to text while preserving layout. Uses OCR technology to extract text from both native PDFs and image-based documents.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | Language code for OCR processing when extracting text from scanned PDFs, images, or JPG documents. Use three-letter ISO 639-2 language codes (e.g., 'eng' for English). Combine multiple languages with… |
| linegrouping | string | – | Controls how text lines are grouped during extraction, particularly within table cells. Choose from mode 1, 2, or 3 for different grouping behaviors. See documentation for detailed mode descriptions. |
| name | string | – | Custom filename for the generated text output file. |
| pages | string | – | Specifies which pages to process using zero-based indices. Supports individual pages (e.g., '0'), ranges (e.g., '3-7'), open-ended ranges (e.g., '10-'), and reverse indexing from the end (e.g., '!0'… |
| rect | string | – | Rectangular region to extract text from, specified as coordinates in the format: x-offset, y-offset, width, height (all in points). Use the PDF Edit Add Helper tool to measure coordinates. If omitted… |
| unwrap | boolean | – | When enabled with line grouping mode 1, unwraps multi-line text within table cells into single lines. Defaults to disabled. |
| url | string | yes | URL of the PDF or image file to convert. Accepts PDF, PNG, and JPG formats. Defaults to a sample PDF if not provided. |
No output schema declared.
No examples provided.
convert_pdf_to_text_fast Convert PDF to Text Fast ~170
Convert a PDF document to plain text using fast, lightweight processing without AI-powered layout analysis or OCR. Use this for quick conversions when layout preservation and scanned page support are not required.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Custom file name for the generated text output. |
| pages | string | – | Comma-separated page indices or ranges to extract (0-based indexing). Supports individual pages (e.g., 0, 5), ranges (e.g., 3-7, 10-), and reverse indexing from the end (e.g., !0 for last page, !5-!2… |
| url | string | yes | URL of the PDF file to convert. Accepts publicly accessible PDF URLs. |
No output schema declared.
No examples provided.
convert_pdf_to_tiff Convert PDF to TIFF ~239
Convert a PDF document to high-quality TIFF image format. Optionally extract specific regions, select page ranges, and customize output file naming.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Custom file name for the generated TIFF output file. |
| pages | string | – | Comma-separated list of pages to convert (0-based indexing). Supports individual pages (e.g., 0, 5), ranges (e.g., 3-7, 10-), and reverse indexing from the end (e.g., !0 for last page, !5-!2 for rang… |
| rect | string | – | Rectangular region to extract from the PDF, specified as four space-separated coordinates: x y width height. Use the PDF Edit Add Helper tool to measure and obtain precise coordinates for your target… |
| unwrap | boolean | – | When enabled with lineGrouping, unwraps text lines within table cells into single lines for cleaner extraction. |
| url | string | yes | URL of the PDF file to convert. Defaults to a sample PDF if not provided. |
No output schema declared.
No examples provided.
convert_pdf_to_unsearchable Convert PDF to Unsearchable ~182
Convert a PDF file into an unsearchable version by rendering it as a flat image, effectively creating a scanned PDF that prevents text extraction.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Output filename for the resulting unsearchable PDF document. |
| pages | string | – | Comma-separated page indices or ranges to process (0-based indexing). Supports individual pages (e.g., 0, 5), ranges (e.g., 3-7, 10-), and reverse indexing from the end (e.g., !0 for last page, !5-!2… |
| url | string | yes | URL of the PDF file to convert. Can be a direct file URL or a cloud storage path (e.g., S3 URI). |
No output schema declared.
No examples provided.
convert_pdf_to_webp Convert PDF to WebP ~222
Convert a PDF document to high-quality WebP image format. Supports selective page extraction and region-based cropping for targeted conversions.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Optional custom file name for the generated WebP output file. |
| pages | string | – | Optional page selection using 0-based indices. Specify individual pages (e.g., 0, 2, 5), ranges (e.g., 3-7, 10-), or reverse indices from the end (e.g., !0 for last page, !5-!2 for range from fifth-t… |
| rect | string | – | Optional rectangular region to extract from the PDF, specified as four space-separated values: x-coordinate, y-coordinate, width, and height. Use this to crop a specific area of interest from the pag… |
| url | string | yes | URL of the PDF file to convert. Accepts publicly accessible PDF URLs or file paths. Defaults to a sample PDF if not specified. |
No output schema declared.
No examples provided.
convert_pdf_to_xls Convert PDF to XLS ~329
Convert a PDF document to Excel (.xls) format while preserving layout, fonts, and table structure. Supports OCR for scanned documents and flexible page selection.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | Language(s) for OCR processing when extracting text from scanned PDFs, images, or JPG documents. Use ISO 639-3 three-letter language codes, optionally combining two languages with a plus sign (e.g.,… |
| linegrouping | string | – | Controls how text lines are grouped during extraction from table cells. Choose from three modes (1, 2, or 3) to adjust grouping behavior. See Line Grouping Options for details on each mode. |
| name | string | – | Custom file name for the generated Excel output file. |
| pages | string | – | Specifies which pages to process using zero-based indices or ranges. Use comma-separated values with formats like: single page (0), range (3-7), open-ended range (10-), or reverse indexing (!0 for la… |
| rect | string | – | Rectangular region to extract from the PDF, specified as four space-separated values: x-coordinate, y-coordinate, width, and height. Use the PDF Edit Add Helper tool to determine coordinates. |
| unwrap | boolean | – | When enabled, unwraps multi-line text within table cells into single lines. Only applies when line grouping mode is set to 1. |
| url | string | yes | URL of the PDF file to convert. Defaults to a sample PDF if not provided. |
No output schema declared.
No examples provided.
convert_pdf_to_xlsx Convert PDF to XLSX ~356
Convert a PDF document to Excel (.xlsx format) while preserving layout, fonts, and table structure. Supports OCR for scanned documents and flexible page selection.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | Language code for OCR processing of scanned PDFs, images, and JPG documents. Use ISO 639-3 three-letter codes (e.g., 'eng' for English). Combine multiple languages with '+' for simultaneous processin… |
| linegrouping | string | – | Controls how text lines are grouped during extraction from table cells. Choose from mode 1, 2, or 3 for different grouping behaviors. See Line Grouping Options for detailed behavior differences. |
| name | string | – | Custom filename for the generated Excel output file. If not specified, a default name will be assigned. |
| pages | string | – | Specifies which pages to process using zero-based indices. Supports individual pages (e.g., '0'), ranges (e.g., '3-7'), open-ended ranges (e.g., '10-'), and reverse indexing (e.g., '!0' for last page… |
| rect | string | – | Rectangular region to extract from the PDF, specified as four space-separated values: x-coordinate, y-coordinate, width, and height. Use the PDF Edit Add Helper tool to determine coordinates. Omit to… |
| unwrap | boolean | – | When enabled with line grouping mode 1, unwraps multi-line text within table cells into single lines. Defaults to disabled. |
| url | string | yes | URL of the PDF file to convert. Defaults to a sample PDF if not provided. |
No output schema declared.
No examples provided.
convert_pdf_to_xml Convert PDF to XML ~366
Convert a PDF document to XML format with detailed extraction of text content, table structures, font information, image references, and precise object positioning data.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | OCR language code for text extraction from scanned PDFs, images, and documents. Use ISO 639-3 three-letter language codes (e.g., 'eng' for English). Combine multiple languages with '+' for simultaneo… |
| linegrouping | string | – | Controls text line grouping behavior during extraction. Mode 1 groups lines within table cells, mode 2 applies alternative grouping, and mode 3 uses a third grouping strategy. See documentation for d… |
| name | string | – | Custom filename for the generated XML output file. If not specified, a default name is assigned. |
| pages | string | – | Comma-separated list of pages to process (0-based indexing). Supports individual pages (e.g., '0,2,5'), ranges (e.g., '3-7'), open-ended ranges (e.g., '10-'), and reverse indexing from end (!0 for la… |
| rect | string | – | Rectangular region to extract from the PDF, specified as space-separated coordinates: x-offset, y-offset, width, and height. Use the PDF Edit Add Helper tool to determine precise coordinates for targ… |
| unwrap | boolean | – | When enabled with line grouping mode 1, unwraps multi-line text within table cells into single continuous lines. Defaults to disabled. |
| url | string | yes | URL of the PDF file to convert. Accepts publicly accessible PDF URLs; defaults to a sample PDF if not provided. |
No output schema declared.
No examples provided.
convert_spreadsheet_to_csv Convert Spreadsheet to CSV ~131
Converts an Excel file (xls/xlsx format) to CSV format. Optionally specify which worksheet to convert and customize the output filename.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Custom filename for the generated CSV output file. If not provided, a default name will be assigned. |
| url | string | yes | URL of the Excel file to convert. Must be a publicly accessible URL pointing to a valid xls or xlsx file. |
| worksheetindex | string | – | Zero-based index of the worksheet to convert (first worksheet is index 1). If not specified, the first worksheet is used by default. |
No output schema declared.
No examples provided.
convert_spreadsheet_to_html Convert Spreadsheet to HTML ~127
Converts Excel (xls/xlsx) or CSV files to HTML format. Supports selecting specific worksheets and customizing the output file name.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Custom name for the generated HTML output file. If not provided, a default name will be used. |
| url | string | yes | URL of the spreadsheet file to convert. Must be a publicly accessible URL pointing to an xls, xlsx, or csv file. |
| worksheetindex | string | – | Zero-based index of the worksheet to convert when the file contains multiple sheets. Defaults to the first worksheet if not specified. |
No output schema declared.
No examples provided.
convert_spreadsheet_to_json Convert Spreadsheet to JSON ~144
Converts Excel (xls/xlsx) or CSV files to JSON format. Supports selecting specific worksheets and customizing output file names.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Custom name for the generated JSON output file. If not provided, a default name will be used. |
| url | string | yes | URL of the spreadsheet file to convert. Must be a publicly accessible URL pointing to an xls, xlsx, or csv file. |
| worksheetindex | string | – | Zero-based index of the worksheet to extract (e.g., 1 for the first sheet, 2 for the second). Only applicable to Excel files with multiple sheets. Omit to use the default sheet. |
No output schema declared.
No examples provided.
convert_spreadsheet_to_pdf Convert Spreadsheet to PDF ~138
Converts Excel (XLS/XLSX) or CSV files to PDF format with optional worksheet selection and automatic page sizing.
| Name | Type | Req | Description |
|---|---|---|---|
| autosize | boolean | – | When enabled, automatically adjusts page dimensions to fit the content. When disabled, uses the worksheet's configured page setup settings. |
| name | string | – | Custom filename for the generated PDF output file. |
| url | string | yes | URL of the spreadsheet file to convert. Accepts XLS, XLSX, or CSV formats. |
| worksheetindex | string | – | Zero-based index of the worksheet to convert when the file contains multiple sheets. Defaults to the first worksheet if not specified. |
No output schema declared.
No examples provided.
convert_spreadsheet_to_text Convert Spreadsheet to Text ~137
Converts Excel spreadsheets (xls, xlsx, or csv files) to plain text format. Optionally specify which worksheet to convert and customize the output filename.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Custom filename for the generated text output file. If not provided, a default name will be assigned. |
| url | string | yes | URL of the spreadsheet file to convert. Must be a publicly accessible URL pointing to an xls, xlsx, or csv file. |
| worksheetindex | string | – | Zero-based index of the worksheet to convert (first worksheet is index 1). If not specified, the first worksheet is used by default. |
No output schema declared.
No examples provided.
convert_spreadsheet_to_xml Convert Spreadsheet to XML ~144
Converts Excel (xls/xlsx) or CSV files to XML format. Supports selecting a specific worksheet from multi-sheet workbooks.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Custom name for the generated XML output file. If not specified, a default name will be used. |
| url | string | yes | URL of the spreadsheet file to convert. Must be a publicly accessible URL pointing to an xls, xlsx, or csv file. |
| worksheetindex | string | – | Zero-based index of the worksheet to convert from multi-sheet workbooks. Use 1 for the first worksheet, 2 for the second, and so on. Only applicable to Excel files with multiple sheets. |
No output schema declared.
No examples provided.
create_file_from_base64 Create File from Base64 ~92
Creates a temporary file from base64-encoded data that can be used with other API methods. The temporary file is automatically deleted after 1 hour.
| Name | Type | Req | Description |
|---|---|---|---|
| file | string | yes | Base64-encoded file content to upload. Must be a valid base64 string representing the file bytes. |
| name | string | – | Optional name for the generated file. If not provided, a default name will be assigned. |
No output schema declared.
No examples provided.
delete_pdf_pages Delete PDF Pages ~194
Removes specified pages from a PDF file and returns the modified document. Pages are identified using 1-based indexing with support for ranges and negative indices (where !1 refers to the last page).
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Filename for the output PDF document. Defaults to 'result.pdf' if not specified. |
| pages | string | – | Comma-separated list of page numbers or ranges to delete, using 1-based indexing. Supports ranges (e.g., 3-5), individual pages (e.g., 2), and negative indices where !1 is the last page (e.g., !1 del… |
| url | string | yes | URL of the PDF file to process. Can be a direct file URL or a path to a PDF stored in cloud storage. |
No output schema declared.
No examples provided.
delete_temporary_file Delete Temporary File ~69
Permanently deletes a temporary file from cloud storage. This operation removes files that were previously uploaded by you or generated by the API.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The S3 URL of the temporary file to delete. This should be a full URL path to the file in the temporary storage bucket. |
No output schema declared.
No examples provided.
delete_text_from_pdf Delete Text from PDF ~292
Remove specified text strings from a PDF document. Supports literal text matching or regex patterns, with options for case sensitivity and limiting replacements per page.
| Name | Type | Req | Description |
|---|---|---|---|
| casesensitive | boolean | – | Control case sensitivity for text matching. When true, searches are case-sensitive; when false, matches ignore case differences. |
| name | string | – | Custom file name for the generated output PDF. If not specified, a default name will be assigned. |
| pages | string | – | Comma-separated page indices or ranges to process (0-based numbering). Use single numbers (e.g., 0, 5), ranges (e.g., 3-7), or open-ended ranges (e.g., 10-). If omitted, all pages are processed. |
| regex | boolean | – | Enable regular expression matching for search strings. When true, searchstrings are interpreted as regex patterns instead of literal text. |
| replacementlimit | number | – | Maximum number of times each search string should be deleted per page. Defaults to 2 deletions per page. |
| searchstrings | array | – | Array of text strings to search for and delete from the PDF. Each string is treated as a literal match unless regex mode is enabled. Defaults to common placeholder tokens like [CLIENT-NAME], [CLIENT-… |
| url | string | yes | URL of the PDF document to process. Defaults to a sample agreement template if not provided. |
No output schema declared.
No examples provided.
extract_data_from_pdf_document Extract Data From PDF Document ~270
Extracts structured data from PDF documents using a customizable parser template. Supports extraction from form fields, tables, and multi-page documents with flexible output formatting.
| Name | Type | Req | Description |
|---|---|---|---|
| generatecsvheaders | boolean | – | When true, includes column headers in CSV output. Only applicable when outputformat is CSV. |
| name | string | – | Optional filename for the generated output file. If not specified, a default name will be assigned. |
| outputformat | string | – | Format for the extracted output data. Choose from JSON, YAML, XML, or CSV. Defaults to JSON. |
| pages | string | – | Specifies which pages to process using 0-based indices. Supports individual pages (e.g., 0, 5), ranges (e.g., 3-7), open-ended ranges (e.g., 10-), and reverse indexing (e.g., !0 for last page). Items… |
| template | string | – | JSON template defining extraction rules, including field patterns (regex-based), table structures with multi-page support, and data type specifications. Defaults to a multi-page table extraction temp… |
| url | string | yes | URL of the PDF document to parse. Can be a remote URL or a local file path accessible to the service. |
No output schema declared.
No examples provided.
extract_email_attachments Extract Email Attachments ~73
Extract all attachments from an email message. Provide the URL to an EML file to retrieve and process its attachments.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The URL pointing to the EML email file to process. Must be a valid, accessible HTTP(S) URL. Defaults to a sample EML file if not provided. |
No output schema declared.
No examples provided.
extract_email_components Extract Email Components ~61
Decode an email message file to extract and parse its components including headers, body, attachments, and metadata.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | URL pointing to the email file (.eml format) to be decoded. Defaults to a sample email file if not provided. |
No output schema declared.
No examples provided.
extract_invoice_data Extract Invoice Data ~146
Extract structured data from invoices using advanced AI. Automatically parse invoice content and return key fields regardless of layout or format, with optional support for custom field extraction.
| Name | Type | Req | Description |
|---|---|---|---|
| callback | string | – | Webhook URL for asynchronous delivery of parsing results. If provided, results will be sent to this endpoint upon completion instead of being returned directly. |
| customfield | string | – | JSON string specifying custom field names to extract beyond standard invoice fields. Use camelCase for field names (e.g., storeNumber, deliveryDate) with multiple fields comma-separated. |
| url | string | yes | URL of the invoice document to process. Accepts PDF and image formats. Defaults to a sample invoice if not provided. |
No output schema declared.
No examples provided.
extract_pdf_attachments Extract PDF Attachments ~61
Extracts all attachments embedded in a PDF file from the provided URL. Returns the extracted attachment data for processing or download.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The URL of the PDF file to extract attachments from. Defaults to a sample PDF file if not provided. |
No output schema declared.
No examples provided.
generate_barcode Generate Barcode ~160
Generate high-quality barcode images in various formats including QR Code, Data Matrix, Code 39, Code 128, PDF417, and other standard barcode types.
| Name | Type | Req | Description |
|---|---|---|---|
| decorationimage | string | – | Optional image file to embed or overlay on the generated barcode for branding or decoration purposes. |
| name | string | – | The output filename for the generated barcode image. Defaults to 'barcode.png' if not provided. |
| type | string | – | The barcode format type to generate. Defaults to QR Code if not specified. Supports formats such as QR Code, Data Matrix, Code 39, Code 128, and PDF417. |
| value | string | – | The data or text to encode in the barcode. Defaults to 'abcdef123456' if not provided. |
No output schema declared.
No examples provided.
get_account_credit_balance Get Account Credit Balance ~26
Retrieve the current credit balance and related account balance information for the authenticated user's account.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_document_parser_template Get Document Parser Template ~41
Retrieve detailed information about a specific document parser template using its unique identifier.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | The unique identifier of the document parser template to retrieve. |
No output schema declared.
No examples provided.
get_file_upload_presigned_url Get File Upload Presigned URL ~94
Generate a pre-signed URL for uploading a file. Use the returned URL with a PUT request to upload your file, then access it via the provided link.
| Name | Type | Req | Description |
|---|---|---|---|
| contenttype | string | – | The MIME type of the file being uploaded (e.g., application/pdf, image/png, text/plain). |
| name | string | – | The name to assign to the uploaded file. Must be provided as a string. |
No output schema declared.
No examples provided.
get_html_template Get HTML Template ~50
Retrieve a specific HTML template by its unique identifier. Use this operation to fetch the full template content for rendering or editing purposes.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | The unique identifier of the HTML template to retrieve. |
No output schema declared.
No examples provided.
get_job_status Get Job Status ~107
Retrieves the current status of an asynchronous background job that was previously initiated through the PDF.co. Use this operation to poll and monitor the progress of long-running tasks.
| Name | Type | Req | Description |
|---|---|---|---|
| force | boolean | – | When enabled, forces a fresh status check from the server rather than returning a cached result, ensuring you get the most current job state. |
| jobid | string | yes | The unique identifier of the asynchronous job whose status you want to check. This ID is returned when you initially create a background job. |
No output schema declared.
No examples provided.
get_pdf_form_fields Get PDF Form Fields ~70
Extract and retrieve metadata about all fillable form fields within a PDF document. Returns field names, types, and properties for programmatic form processing.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The URL of the PDF file to analyze. Must be a publicly accessible URL pointing to a valid PDF document containing form fields. |
No output schema declared.
No examples provided.
get_pdf_info Get PDF Info ~53
Retrieve detailed metadata, properties, and security permissions for a PDF document from a specified URL.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The URL of the PDF document to analyze. Must be a valid, publicly accessible PDF file URL. |
No output schema declared.
No examples provided.
list_document_parser_templates List Document Parser Templates ~36
Retrieve all available Document Parser data extraction templates accessible to the current user. Use this to discover template options before configuring document parsing operations.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_templates_html List HTML Templates ~34
Retrieve all HTML templates available for the current user. Returns a collection of template resources that can be used for rendering or customization.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
What is the com.mcparmory/pdfco MCP server?
com.mcparmory/pdfco is an MCP server listed in the public MCP registry as com.mcparmory/pdfco. Extract data, edit, convert, and parse PDF documents with OCR and AI. This page covers its container image (ghcr.io/mcparmory/pdfco:1.0.2).
Is the com.mcparmory/pdfco MCP server safe to use?
com.mcparmory/pdfco scores 47 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the com.mcparmory/pdfco MCP server expose?
com.mcparmory/pdfco exposes 65 tools: extract_invoice_data, extract_data_from_pdf_document, list_document_parser_templates, get_document_parser_template, extract_pdf_attachments, and 60 more. Their descriptions and schemas cost roughly 12,004 tokens of context every time the server is loaded.
Is the com.mcparmory/pdfco MCP server still maintained?
com.mcparmory/pdfco is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.