com.mcparmory/pdfco
PYPI · MCPARMORY-PDFCO · 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 Security87
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Install-script risk not yet assessed.Unverified
- 2 of 41 dependencies flagged as unhealthy. View diagnostics → Partial
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: the license (MIT License) isn't a recognized OSI-approved license. 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 Management87
- Stability observed for 26 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 current MCP spec version (2026-07-28).Pass
How do I install the com.mcparmory/pdfco MCP server?
com.mcparmory/pdfco runs locally as a PyPI package, launched with uvx mcparmory-pdfco. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · mcparmory-pdfco
claude mcp add com-mcparmory-pdfco -- uvx mcparmory-pdfco
{
"mcpServers": {
"com-mcparmory-pdfco": {
"command": "uvx",
"args": [
"mcparmory-pdfco"
]
}
}
} {
"servers": {
"com-mcparmory-pdfco": {
"command": "uvx",
"args": [
"mcparmory-pdfco"
]
}
}
} codex mcp add com-mcparmory-pdfco -- uvx mcparmory-pdfco
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"com-mcparmory-pdfco": {
"type": "local",
"command": [
"uvx",
"mcparmory-pdfco"
],
"enabled": true
}
}
} openclaw mcp add com-mcparmory-pdfco --command uvx --arg mcparmory-pdfco
mcp_servers:
com-mcparmory-pdfco:
command: "uvx"
args: ["mcparmory-pdfco"] {
"McpServers": {
"com-mcparmory-pdfco": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"mcparmory-pdfco"
]
}
}
} assistant mcp add com-mcparmory-pdfco -t stdio -c uvx -a mcparmory-pdfco
{
"mcpServers": {
"com-mcparmory-pdfco": {
"command": "uvx",
"args": [
"mcparmory-pdfco"
]
}
}
} 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.
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Sept 26 −3
- Stability: pass → 0.77 functional
- 16 Sept 26 +1
- Stability: 0.97 → pass security
- 15 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 14 Sept 26 −15
- Malware scan: pass → unverified ▼ security
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Sept 26 −2
- Stability: pass → 0.83 functional
- 10 Sept 26 +1
- Stability: 0.97 → pass security
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 pypi/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 | pypi |
Background: How many MCP packages publish verified provenance →
Dependencies 41 packages
| Packages resolved | 41 |
|---|---|
| Stale | 1 |
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
make_pdf_searchable Make PDF Searchable ~254
Convert scanned PDF documents or image files into text-searchable PDFs by running OCR and adding an invisible text layer for search and indexing capabilities.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | Language code for OCR processing (e.g., 'eng' for English). Defaults to English if not specified. Use standard ISO 639-3 language codes. |
| name | string | – | Output filename for the resulting searchable PDF. Defaults to 'result.pdf' if not specified. |
| 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 (e.g., !0 for last page). Whitespace is all… |
| rect | string | – | Rectangular region coordinates for targeted OCR processing, specified as four space-separated values: x y width height (in points). Use the PDF Edit Add Helper tool to measure coordinates. If omitted… |
| url | string | yes | URL of the PDF or image file to process. Accepts remote URLs pointing to scanned documents or image files that need OCR conversion. |
No output schema declared.
No examples provided.
merge_documents_to_pdf Merge Documents to PDF ~142
Merge multiple documents and images of various formats (PDF, DOC, DOCX, XLS, XLSX, RTF, TXT, PNG, JPG, or ZIP archives) into a single PDF file. This operation supports broader file type compatibility than standard PDF merge but consumes additional credits due to internal format conversions.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Optional custom filename for the generated PDF output file. |
| url | string | yes | Comma-separated URLs of source files to merge. Supports PDF, DOC, DOCX, XLS, XLSX, RTF, TXT, PNG, JPG, and ZIP files containing documents or images. Multiple files are merged in the order specified. |
No output schema declared.
No examples provided.
merge_pdfs Merge PDFs ~100
Merge multiple PDF files into a single consolidated PDF document. Provide one or more PDF URLs to combine them in the order specified.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | The filename for the resulting merged PDF document. Defaults to 'result.pdf' if not specified. |
| url | string | yes | One or more URLs pointing to PDF files to merge, separated by commas. URLs must be accessible and point to valid PDF documents. Defaults to sample encrypted PDFs if not specified. |
No output schema declared.
No examples provided.
read_barcodes_from_url Read Barcodes from URL ~210
Decode barcodes and QR codes from images or PDF documents accessible via URL. Supports 40+ barcode formats including QR Code, Code 128, EAN, DataMatrix, PDF417, and GS1 standards.
| Name | Type | Req | Description |
|---|---|---|---|
| pages | string | – | Optional page indices or ranges to scan (0-based, applies to PDFs only). Specify individual pages (e.g., 0,2,5), ranges (e.g., 3-7 or 10-), or reverse indices (e.g., !0 for last page). Comma-separate… |
| types | string | yes | Comma-separated list of barcode types to detect. Choose from 40+ supported formats including QRCode, Code128, EAN13, DataMatrix, PDF417, GS1, and others. Only specified types will be decoded. |
| url | string | yes | URL of the image or PDF document to scan for barcodes. Must be publicly accessible. |
No output schema declared.
No examples provided.
remove_pdf_password Remove PDF Password ~83
Remove password protection and access restrictions from a PDF file, making it fully accessible without authentication.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | The desired filename for the unprotected PDF output. Defaults to 'unprotected' if not specified. |
| url | string | yes | The URL of the PDF file to remove password protection from. Can be a direct file URL or a cloud storage link. |
No output schema declared.
No examples provided.
replace_text_in_pdf Replace Text in PDF ~288
Search for text patterns in a PDF document and replace them with new text. Supports literal string matching or regular expressions, with options for case sensitivity and replacement limits.
| Name | Type | Req | Description |
|---|---|---|---|
| casesensitive | boolean | – | Perform case-sensitive text matching. When true, 'Hello' and 'hello' are treated as different strings. |
| name | string | – | Output filename for the processed PDF document. |
| pages | string | – | Comma-separated page indices or ranges to process (0-based indexing). Supports ranges (e.g., 3-7), open-ended ranges (e.g., 10-), and reverse indexing (e.g., !0 for last page). If omitted, all pages… |
| regex | boolean | – | Enable regular expression matching for search strings. When true, searchstrings are interpreted as regex patterns rather than literal text. |
| replacementlimit | number | – | Maximum number of replacements to perform per search string. Defaults to 1 replacement per string. |
| replacestrings | array | – | Array of replacement text strings corresponding to each search string. Must have the same length as searchstrings for proper pairing. |
| searchstrings | array | – | Array of text strings or patterns to search for in the PDF. Order corresponds to replacestrings array for paired replacements. |
| url | string | yes | URL of the PDF file to process. Defaults to a sample agreement template if not specified. |
No output schema declared.
No examples provided.
replace_text_with_image_in_pdf Replace Text with Image in PDF ~307
Search for specific text in a PDF document and replace it with an image. Supports regex patterns and case-sensitive matching with optional replacement limits and page range targeting.
| Name | Type | Req | Description |
|---|---|---|---|
| casesensitive | boolean | – | Perform case-sensitive text matching. When true, 'Text' and 'text' are treated as different; when false, they match regardless of case. |
| name | string | – | Custom filename for the generated output PDF. If not specified, a default name is assigned. |
| pages | string | – | Comma-separated page indices or ranges to process (0-based indexing). Supports ranges (e.g., 3-7), open-ended ranges (e.g., 10-), reverse indexing (e.g., !0 for last page), and individual pages. Omit… |
| regex | boolean | – | Enable regular expression matching for the search string. When true, the search string is interpreted as a regex pattern; when false, performs literal text matching. |
| replaceimage | string | – | Base64-encoded image data (with data URI prefix) to use as the replacement. Supports PNG, JPEG, and other common image formats. |
| replacementlimit | number | – | Maximum number of replacements to perform per search term. Use 0 to replace all occurrences; any positive integer limits replacements to that count. |
| searchstring | string | – | – |
| url | string | yes | URL of the PDF file to modify. Accepts publicly accessible URLs or data URIs. |
No output schema declared.
No examples provided.
rotate_pdf_pages Rotate PDF Pages ~210
Rotates specified pages in a PDF document by a given angle. If no pages are specified, the operation rotates all pages in the document.
| Name | Type | Req | Description |
|---|---|---|---|
| angle | string | – | The rotation angle in degrees to apply to selected pages. Common values are 90, 180, and 270 for standard rotations. |
| name | string | – | The filename for the output PDF document after rotation is applied. |
| pages | string | – | Zero-based page indices or ranges to rotate, specified as comma-separated values. Supports individual pages (e.g., 0, 2, 5), ranges (e.g., 3-7, 10-), and reverse indexing from the end of the document… |
| url | string | yes | The URL of the PDF file to rotate. Can be a remote URL or a local file path. |
No output schema declared.
No examples provided.
search_pdf_text Search PDF Text ~287
Search for text patterns in a PDF document and retrieve their precise coordinates. Supports both literal string matching and regular expression patterns for flexible text discovery.
| Name | Type | Req | Description |
|---|---|---|---|
| casesensitive | boolean | – | Control search sensitivity to letter case. Set to false for case-insensitive matching; true for case-sensitive matching. |
| name | string | – | Name identifier for the output results. |
| pages | string | – | Specify which pages to search using 0-based indices. Supports individual pages (e.g., 0, 5), ranges (e.g., 3-7, 10-), and reverse indexing (e.g., !0 for last page). Use comma-separated values for mul… |
| regexsearch | boolean | – | Enable regular expression matching for the search string. When true, the search string is interpreted as a regex pattern; when false, performs literal string matching. |
| searchstring | string | yes | Text or pattern to find in the PDF. When regex search is enabled, this accepts regular expression syntax (e.g., date patterns like \d+/\d+/\d+). |
| url | string | yes | URL of the PDF file to search. Defaults to a sample PDF if not specified. |
| wordmatchingmode | string | – | Word matching mode to control how text boundaries are handled during search (e.g., whole words only vs. partial matches). |
No output schema declared.
No examples provided.
search_tables_in_pdf Search Tables in PDF ~165
Scan a PDF document using AI to detect and extract tables, returning their locations, coordinates, and column information for specified pages.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Optional custom name for the generated output file. |
| pages | string | – | Comma-separated page indices or ranges to scan (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 fo… |
| url | string | yes | URL of the PDF file to analyze. Defaults to a sample PDF if not provided. |
No output schema declared.
No examples provided.
send_email_with_attachment Send Email with Attachment ~293
Send an email message with optional file attachment. Supports multiple recipients and requires SMTP server credentials for delivery.
| Name | Type | Req | Description |
|---|---|---|---|
| bcc | string | – | Blind carbon copy recipient email address. Use comma-separated values for multiple recipients. Recipients in this field are hidden from other recipients. |
| cc | string | – | Carbon copy recipient email address. Use comma-separated values for multiple recipients. |
| from | string | yes | Sender email address in the format 'Name <email@domain.com>' or just 'email@domain.com'. |
| name | string | – | Custom filename for the attachment. If not specified, the original filename from the URL will be used. |
| replyto | string | – | Reply-to email address. If specified, replies will be directed to this address instead of the sender. |
| smtppassword | string | yes | Password or app-specific password for SMTP authentication. For Gmail, use an app-specific password rather than your account password. |
| smtpserver | string | yes | SMTP server hostname (e.g., smtp.gmail.com for Gmail, smtp.office365.com for Outlook). |
| smtpusername | string | yes | Username or email address for SMTP authentication. |
| subject | string | yes | Email subject line. |
| to | string | yes | Primary recipient email address. Use comma-separated values for multiple recipients. |
| url | string | yes | URL of the file to attach to the email. Defaults to a sample PDF from AWS S3. |
No output schema declared.
No examples provided.
split_pdf Split PDF ~186
Split a PDF document into multiple separate PDF files by specifying which pages to extract using page numbers or ranges.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Filename for the output PDF file. Defaults to 'result.pdf' if not specified. |
| pages | string | – | Pages to extract from the PDF using 1-based indexing. Specify individual pages (e.g., 1,3,5), ranges (e.g., 1-5), or combinations (e.g., 1-3,5,7-9). Use !1 to reference the last page and !6-!2 for ra… |
| url | string | yes | URL of the PDF file to split. Accepts any publicly accessible PDF URL; defaults to a sample PDF if not provided. |
No output schema declared.
No examples provided.
split_pdf_by_text_search Split PDF by Text Search ~305
Split a PDF document into multiple files by searching for specific text patterns or barcodes. Pages containing the search term can be used as split points, with options to exclude or include those pages in the output.
| Name | Type | Req | Description |
|---|---|---|---|
| casesensitive | boolean | – | Perform case-sensitive text matching. When disabled, search is case-insensitive. |
| excludekeypages | boolean | – | Exclude pages containing the search match from the output files. When enabled, matching pages are removed; when disabled, they are included in the split results. |
| lang | string | – | OCR language for extracting text from scanned PDFs, images, and documents. Use ISO 639-3 language codes (e.g., 'eng' for English). Combine multiple languages with '+' for simultaneous processing (e.g… |
| name | string | – | Base name for the output PDF files. The system will append sequential numbering to create individual split file names. |
| regexsearch | boolean | – | Enable regular expression matching for the search string. When enabled, the searchstring is interpreted as a regex pattern rather than literal text. |
| searchstring | string | yes | Text pattern or barcode format to search for within the PDF. Supports barcode syntax like [[barcode:qrcode,datamatrix /pattern/]] for barcode detection, or plain text strings for text search. |
| url | string | yes | URL of the PDF file to split. Must be a publicly accessible URL pointing to a valid PDF document. |
No output schema declared.
No examples provided.
upload_file_from_url Upload File from URL ~95
Downloads a file from a source URL and uploads it as a temporary file to the system. Temporary files are automatically deleted after 1 hour.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Optional custom name for the uploaded file. If not provided, the original filename from the source URL will be used. |
| url | string | yes | The source URL of the file to download and upload. Must be a valid, accessible HTTP or HTTPS URL. |
No output schema declared.
No examples provided.
upload_file_from_url_direct Upload File From URL ~95
Downloads a file from a remote URL and uploads it as a temporary file to the system. The temporary file will be automatically deleted after 1 hour.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Optional custom name for the uploaded file. If not provided, the original filename from the source URL will be used. |
| url | string | yes | The remote URL pointing to the file to download and upload. Must be a valid URI format. |
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 PyPI package (mcparmory-pdfco).
Is the com.mcparmory/pdfco MCP server safe to use?
com.mcparmory/pdfco scores 74 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. 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.