PDF.co
PDF.co is a REST API platform for PDF automation including PDF extraction, generation, editing, splitting, merging, form filling, barcode processing, OCR, document parsing, file conversion (PDF to Excel/CSV/JSON/XML/HTML/Image and vice versa), and AI-powered invoice parsing.
Verdict
Common use cases
- OCR scanned invoices for data entry
- Convert client emails to archival PDFs
- Extract Excel tables as JSON for reports
- Overlay signatures on contract PDFs
- Make image-only PDFs text-searchable
Integration
- Vendor
- PDF.co
- Category
- docs
- Auth
- API_KEY
- Tools
- 33
- Composio slug
pdf_co
Tools
- Add Content to PDF
Tool to add content to an existing pdf. use when you need to overlay text, images, barcodes, or links before distributing the file.
- Change PDF Text Searchable
Tool to make pdf text searchable using ocr. use when you need to add a searchable text layer to scanned or image-only pdf documents.
- Check Job Status
Tool to check status and result of an asynchronous job. use after submitting a job to poll for completion.
- Convert Email to PDF
Tool to convert email files (.eml/.msg) to pdf. use when you need to transform standalone email messages into pdf documents.
- Convert Excel to CSV
Tool to convert an excel file (xls/xlsx) to csv. use when you have a public excel file url and need csv output. inline option returns data inline; otherwise provides download url.
- Convert Excel to HTML
Tool to convert an excel file to html. use when you have an excel url or file bytes and need html output.
- Convert Excel to JSON
Tool to convert an online excel or csv file to json format. use when you have a public file url and need structured data extraction.
- Convert Excel to Text
Tool to convert excel files to plain text. use after providing an excel file url to extract spreadsheet content.
- Convert Excel to XML
Tool to convert an excel file to xml. use when needing xml output from xls/xlsx/csv synchronously or asynchronously.
- Convert HTML to PDF
Tool to convert html code or webpage url into a pdf document. use when you need to capture a webpage or html snippet as a pdf file.
- Convert PDF to CSV
Tool to convert pdf or scanned images to csv format. use when you need to extract tabular data from a pdf into csv format.
- Convert PDF to HTML
Tool to convert pdf documents to html. use when you need an html rendition of a pdf or scanned image.
- Convert PDF to Image
Tool to convert pdf pages to images (png, jpg, tiff). use when you need image previews of pdf content.
- Convert PDF to JSON
Tool to convert pdf or scanned images to json format. use when you need a structured json representation of pdf content.
- Convert PDF to Text
Tool to convert pdf or scanned images to plain text. use when you need raw text output preserving layout.
- Convert PDF to XLS
Tool to convert pdf or scanned images to xls format. use when you need to extract tabular data into an excel spreadsheet.
- Convert PDF to XLSX
Tool to convert pdf or scanned images to xlsx (excel) format. use when you need structured spreadsheet output from a pdf.
- Convert PDF to XML
Tool to convert pdf or scanned images to xml format. use when you need to extract structured data from pdf into xml.
- Convert Text to PDF
Tool to convert plain text data to pdf. use when you need to generate a pdf from raw text content or text file links.
- Delete PDF Pagesdestructive
Tool to delete specific pages from a pdf file. use when you need to remove unwanted pages before further processing.
- Document Parser
Tool to parse documents based on predefined templates to extract structured data. use when you need to extract structured fields from a pdf by supplying a custom template.
- Extract PDF Attachments
Tool to extract embedded attachments from a pdf. use when you need to retrieve embedded files from a pdf after uploading.
- Find Text in PDF
Tool to find text in a pdf document. use when you need to locate keywords or regex patterns and get their page positions.
- Generate Barcode
Tool to generate barcode images (qr, code128, code39, pdf417, etc.). use when you need to encode data into barcodes on the fly.
- Get Account Balance Info
Tool to get account balance info. use after authenticating to check remaining credits.
- Merge PDFs
Tool to merge multiple pdf files into one document. use when you need to combine several pdf urls into a single pdf file.
- PDF Forms Info Reader
Tool to extract form field information from a pdf. use when you need to retrieve names, types, and values of form fields.
- PDF Info Reader
Tool to retrieve detailed information and metadata of a pdf. use when you need page count, author, encryption details, and other document properties.
- Rotate PDF Pages
Tool to rotate selected pages in a pdf. use when you need to adjust the orientation of specific pages in an online pdf file before further processing.
- Search and Delete Text in PDFdestructive
Tool to search for and delete text in a pdf by keyword or regex. use when you need to remove sensitive or unwanted text from a pdf document.
- Search and Replace Text in PDF
Tool to search for and replace text in a pdf document. use when you need to update specific text instances within an existing pdf file (e.g., changing invoice numbers).
- Split PDF
Tool to split a pdf into multiple files by page ranges. use when you need to extract specific pages or page ranges from a pdf.
- Upload File
Tool to upload a local file to pdf.co. use when you need to stage a document on pdf.co for downstream processing.
Setup
Setup guide
- 11. Open your Switchy workspace and navigate to Settings > Integrations > Add MCP Server. 2. Select PDF.co from the catalog and choose API Key as the authentication method. 3. Log in to your PDF.co account at pdf.co, go to API Keys under your account settings, and copy your key. 4. Paste the API key into Switchy's connection form and click Connect. 5. Return to any Space and type '@PDF.co check job status' with a dummy job ID to confirm the connection works—you'll see an error about an invalid ID, which means the MCP is responding. 6. To invoke a tool, @mention PDF.co in a message, describe the task (e.g. 'convert this Excel file to JSON'), and include a public URL to the file. 7. For async jobs like OCR, PDF.co returns a job ID—wait a few seconds, then @mention it again with 'check job status' and the ID to retrieve the result.
What teammates see: by default, memories from PDF.co are scoped to the Space (PROJECT visibility) - you can mark any memory PRIVATE or share it ORG-wide.
Works well with
Top models
Compatibility data appears once enough Spaces have used this MCP together with a given model.
How Switchy teams use it
Starter prompts
OCR Scanned Invoice
@PDF.co make this PDF text searchable: [paste public URL]. Return the download link when it's ready.Open in a Space →
Email to PDF Archive
@PDF.co convert this email file to PDF: [paste public URL]. I need it for our project archive.Open in a Space →
Excel to JSON Extract
@PDF.co convert this Excel file to JSON: [paste public URL]. I want the first sheet as an array of objects.Open in a Space →
Add Signature Overlay
@PDF.co add this signature image to page 1 of the PDF at coordinates (400, 650): [paste PDF URL and image URL].Open in a Space →
Excel to CSV Export
@PDF.co convert this Excel file to CSV: [paste public URL]. Return the CSV inline if it's under 1MB.Open in a Space →
Example outputs
Illustrative - representative of the model's voice and quality, not literal recordings.
@PDF.co I have a scanned contract at https://example.com/contract.pdf — can you make the text searchable so I can copy-paste clauses?
I've submitted your PDF for OCR processing. The job is running asynchronously and should complete in 15-30 seconds depending on page count. Once finished, you'll receive a new PDF with a searchable text layer overlaid on the original scanned images. The visual appearance won't change, but you'll be able to select and copy text. I'll check the job status now… Job complete. Your searchable PDF is ready at https://pdf.co/v1/file/abc123/contract-searchable.pdf (link expires in 60 minutes).
This example highlights PDF.co's OCR capability, which is useful for legacy documents. Note that processing happens asynchronously — you'll need to poll job status or wait for a webhook. The output URL is temporary, so download promptly. API key must have OCR permissions enabled.
@PDF.co Add a 'CONFIDENTIAL' watermark in red 48pt Arial across every page of https://example.com/report.pdf before I share it with the client.
I've added a diagonal 'CONFIDENTIAL' watermark in red (RGB 255,0,0) at 48pt Arial across all pages of your report. The watermark is semi-transparent so underlying content remains readable. Your modified PDF is available at https://pdf.co/v1/file/def456/report-watermarked.pdf (expires in 60 minutes). This is a permanent change — the watermark is embedded in the PDF structure, not a removable annotation.
This demonstrates PDF.co's content-addition tool, which can overlay text, images, or barcodes. The watermark is baked into the PDF, so recipients can't remove it. Be aware that large files may take longer to process, and the temporary download link requires prompt action. Useful for branding or confidentiality marking before distribution.
@PDF.co I need to extract data from this Excel invoice at https://example.com/invoice.xlsx — convert it to JSON so I can parse line items programmatically.
I've converted your Excel invoice to JSON. The output contains an array of objects, one per row, with keys matching your column headers ('Item', 'Quantity', 'Unit Price', 'Total'). Here's a sample: [{"Item":"Widget A","Quantity":5,"Unit Price":12.50,"Total":62.50}, …]. The full JSON is available at https://pdf.co/v1/file/ghi789/invoice.json (expires in 60 minutes). This format is ready for parsing with standard JSON libraries in any language.
This example shows PDF.co's Excel-to-JSON conversion, which is valuable for integrating spreadsheet data into automated workflows. The tool assumes the first row contains headers. Complex Excel features (formulas, merged cells, multiple sheets) may not translate perfectly — inspect the output before relying on it in production. Requires a publicly accessible Excel file URL.
Use-case deep-dives
When PDF.co fits high-volume contract prep
A 6-person sales ops team closes 40-60 deals a month, each needing a custom NDA with client logo, signature fields, and watermark before DocuSign. PDF.co's 'Add Content to PDF' tool handles the overlay work in a Zapier chain: CRM trigger → fetch template → stamp logo and date → route to signer. The API key auth means no OAuth dance, so setup takes 20 minutes. The catch: if your contracts need conditional clauses or multi-step approvals, you're still writing that logic outside the MCP—PDF.co just does the stamping. For straight-through processing at this volume, it removes the manual Acrobat step and keeps the team in their CRM.
OCR plus structured export for receipt processing
A 3-person accounting firm gets 200 vendor invoices a month as scanned PDFs. They use PDF.co's 'Change PDF Text Searchable' to OCR the scans, then 'Convert Excel to JSON' to pull line items from any Excel attachments into their bookkeeping software. The async job polling ('Check Job Status') means they can batch-process overnight without blocking. The limit: if invoices are handwritten or low-quality faxes, OCR accuracy drops below 85% and you're back to manual review. For typed invoices from repeat vendors, this cuts data entry from 4 hours to 30 minutes a week. The API key setup means the firm's junior bookkeeper can own the integration without IT.
Email-to-PDF for compliance and case records
A 10-person support team at a healthcare SaaS needs to archive every customer email thread as a PDF for HIPAA audit trails. PDF.co's 'Convert Email to PDF' tool runs in a Zendesk webhook: ticket closed → export .eml → convert → store in S3 with case ID. The 33-tool catalog also covers edge cases like converting attached Excel reports to searchable text for the knowledge base. The trade-off: if your email volume exceeds 500 conversions a day, PDF.co's per-page pricing adds up faster than running Puppeteer on a $20/month VPS. For teams under that threshold who don't want to maintain conversion infrastructure, this MCP keeps compliance simple and the support team focused on tickets.
Frequently asked
What does the PDF.co MCP do in Switchy?
It lets your AI agents convert, edit, and extract data from PDFs and Office files without manual uploads. The MCP wraps PDF.co's 33 tools — OCR for scanned docs, Excel-to-JSON conversion, adding watermarks or barcodes to PDFs, and email-to-PDF rendering. Your team asks the AI to process a file URL, and the MCP returns the result or a download link.
Do I need a PDF.co account to use this MCP?
Yes. You need a PDF.co API key, which requires signing up at PDF.co and choosing a plan. The free tier gives you 150 credits per month; paid plans start at $9.99 for 5,000 credits. Paste the API key into Switchy's MCP settings once, and all team members can use it through the AI without touching PDF.co's dashboard.
Can the MCP edit PDFs stored in Google Drive or Dropbox?
Only if you share a public URL to the file. The MCP tools expect a direct HTTP link to the PDF or Excel file — they don't browse your cloud storage. If your file is private, you'll need to generate a temporary share link first, or upload it to a public bucket. The MCP doesn't handle OAuth to third-party storage.
How is this different from uploading files to PDF.co's website?
The MCP runs inside your AI workflow, so you skip the upload-download-copy-paste loop. Instead of visiting PDF.co, dragging a file, waiting, then pasting the output into Slack, you ask Switchy's AI to convert or OCR the file. The AI calls the MCP, polls the job status, and returns the result in the same chat thread.
Who should connect the PDF.co MCP to Switchy?
Whoever holds your PDF.co API key — usually a team admin or the person who pays for the PDF.co subscription. Once connected, the MCP is shared across your Switchy workspace, so anyone can trigger PDF jobs through the AI. Usage counts against your PDF.co credit balance, not Switchy's plan limits.