What can you do with this server?

The FileToPDF MCP server lets you convert files, HTML, and Markdown to PDF using natural language commands, with options for layout, passwords, and accessibility. * Check account status (get_account): Verify your API key and view your plan, remaining credits, and subscription status — free, uses no credits. * Convert files from a URL (convert_file): Convert public URLs of Office documents (DOCX, XLSX, PPTX, ODT, RTF, TXT, CSV), images (PNG, JPG, WebP), HTML, Markdown, or existing PDFs into PDFs. * Convert raw HTML to PDF (convert_html): Render HTML strings with optional CSS injection and full layout control (paper size, margins, scale, orientation, print background) using Chromium. * Convert raw Markdown to PDF (convert_markdown): Render Markdown strings to clean PDFs with a sensible default stylesheet (overridable with custom CSS) and the same layout options as HTML conversion. * Customize output: Control page orientation, paper dimensions, margins, scale, page ranges, and background printing. * Protect PDFs: Set user and owner passwords to restrict opening or permissions on the output PDF. * Accessibility & archiving: Produce PDF/UA (accessible) or PDF/A (archival) compliant documents (Pro/Scale/trial plans only). * Save locally: Write output PDFs to disk via a save_path parameter or the FILETOPDF_OUTPUT_DIR environment variable. * Cost: Each successful conversion costs 1 credit; errors are free.

Which integrations are available for this server?

Allows CrewAI agents to convert files, HTML, and Markdown to PDF as part of their workflows. Integrates with LangChain agents to convert files, HTML, and Markdown to PDF. Enables Langflow workflows to convert files, HTML, and Markdown to PDF. Allows Make (formerly Integromat) scenarios to convert files, HTML, and Markdown to PDF. Enables n8n workflows to convert files, HTML, and Markdown to PDF. Works with OpenAI Agents SDK to convert files, HTML, and Markdown to PDF. Integrates with Vercel AI SDK to convert files, HTML, and Markdown to PDF. Allows Zapier Zaps to convert files, HTML, and Markdown to PDF.

How do I use FileToPDF MCP server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@FileToPDF MCP server convert this markdown to PDF" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

FileToPDF MCP server

Official

by FileToPDF

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

FileToPDF MCP server

npm Install MCP Server

A Model Context Protocol server for FileToPDF. It lets any MCP client — Claude Desktop, Claude Code, Cursor, Cline, VS Code, ChatGPT, n8n, Make, or your own agent — convert files, HTML, and Markdown to PDF through natural language: invoices, reports, documentation, DOCX/XLSX/PPTX, images, web pages, and more.

Bring your own API key — get one free, in one click, at https://filetopdf.dev (10 free conversions, no signup required).

Tools

Tool	What it does
`get_account`	Check the API key and show plan + remaining credits. Free, no credits used.
`convert_file`	Convert a file from a public URL (DOCX, XLSX, PPTX, images, HTML, MD, PDF…) to PDF.
`convert_html`	Render a raw HTML string (with optional CSS + layout options) to a pixel-perfect PDF via Chromium.
`convert_markdown`	Render a raw Markdown string (with optional CSS + layout options) to a clean PDF.

Each convert tool returns a metadata summary and the PDF as an embedded application/pdf resource (base64), so capable clients can save the file. Set the FILETOPDF_OUTPUT_DIR env var, or pass save_path, to also write the PDF to disk.

Layout options (landscape, paperWidth/Height, margins, scale, pdfa, passwords, …) are available on Pro, Scale, and the free trial; on Starter/Basic they return an upgrade error. Each successful conversion costs 1 credit; errors are free.

Related MCP server: PDF Manipulation MCP Server

Quick start (local / stdio)

Cursor — one-click install: Add to Cursor (then replace the placeholder with your key).

Claude Desktop / Cline / any stdio client — add to the MCP config (claude_desktop_config.json, cline_mcp_settings.json, …):

{
  "mcpServers": {
    "filetopdf": {
      "command": "npx",
      "args": ["-y", "filetopdf-mcp"],
      "env": { "FILETOPDF_API_KEY": "sk_live_YOUR_API_KEY" }
    }
  }
}

Claude Code:

claude mcp add filetopdf -e FILETOPDF_API_KEY=sk_live_YOUR_API_KEY -- npx -y filetopdf-mcp

VS Code (.vscode/mcp.json or via MCP: Add Server):

{
  "servers": {
    "filetopdf": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "filetopdf-mcp"],
      "env": { "FILETOPDF_API_KEY": "sk_live_YOUR_API_KEY" }
    }
  }
}

Hosted / remote (Streamable HTTP) — no install

A hosted endpoint is available at https://api.filetopdf.dev/mcp. Authenticate with your own key via the x-api-key header, an Authorization: Bearer header, or an ?apiKey= query parameter.

{
  "mcpServers": {
    "filetopdf": {
      "type": "streamable-http",
      "url": "https://api.filetopdf.dev/mcp",
      "headers": { "x-api-key": "sk_live_YOUR_API_KEY" }
    }
  }
}

This is also the URL to paste into any platform with an MCP client step — n8n (MCP Client Tool), Make (MCP Client), Zapier (MCP Client beta), Relay.app (Call MCP tool), Flowise, Langflow, Dify, LibreChat, AnythingLLM, or agent frameworks (OpenAI Agents SDK, LangChain, CrewAI, Vercel AI SDK).

To self-host instead:

npm run build && npm run start:http   # listens on $PORT (default 8080) at /mcp

A Dockerfile is included for container hosting (Smithery, Fly, Render, Cloud Run).

Develop & test

npm install
npm run build          # tsc -> dist/
npm test               # spawns the built stdio server, runs a live conversion

npm test reads FILETOPDF_API_KEY, or API_KEY= from a gitignored .env.

License

MIT

Available Tools

4 tools

convert_fileConvert a file (by URL) to PDFAInspect

Convert a file fetched from a public URL into a PDF. Auto-detects the engine from the extension: Office docs (DOCX, XLSX, PPTX, ODT, RTF, TXT, CSV…), images (PNG, JPG, WebP…), HTML, Markdown, or an existing PDF (passthrough). Costs 1 credit on success. Returns the PDF as an embedded resource.

ParametersJSON Schema

Name	Required	Description
`url`	Yes	Public http(s) URL of the file to download and convert.
`landscape`	No	Render in landscape orientation. (Pro/Scale/trial only.)
`nativePageRanges`	No	Page ranges to include, e.g. "1-3".
`password`	No	Password to open a protected source document.
`pdfa`	No	PDF/A conformance level, e.g. "PDF/A-2b". (Pro/Scale/trial only.)
`pdfua`	No	Produce an accessible PDF/UA document.
`userPassword`	No	Password required to open the resulting PDF.
`ownerPassword`	No	Owner password controlling permissions on the resulting PDF.
`save_path`	No	Optional absolute path to also write the PDF to on disk.

TDQS

A3.9/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses important behavioral details beyond annotations: it costs 1 credit, returns an embedded resource, and auto-detects engine. With only openWorldHint annotation, this adds significant transparency, though it could mention error scenarios or size limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loading the core action, then efficiently listing supported types and cost. No redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 9 parameters and no output schema, the description covers the main function and return format but lacks details on parameter interactions, error handling, or limits. It is adequate but not fully comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description does not add meaningful semantics beyond the schema for individual parameters; it focuses on high-level tool behavior instead of enriching parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool converts a file from a public URL to PDF, lists supported formats, and mentions auto-detection of the engine. It distinguishes from siblings like convert_html and convert_markdown by covering those plus many more types.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use (for general file conversion to PDF) but does not explicitly state when not to use or compare with sibling tools. It lacks guidance on choosing between convert_file and the more specific convert_html or convert_markdown.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

convert_htmlConvert HTML to PDFAInspect

Render a raw HTML string to a PDF using Chromium, with optional CSS and layout options. Costs 1 credit on success. Returns the PDF as an embedded resource.

ParametersJSON Schema

Name	Required	Description
`html`	Yes	The HTML markup to render.
`css`	No	Optional CSS, injected into the document <head>.
`landscape`	No	Render in landscape orientation. (Pro/Scale/trial only.)
`paperWidth`	No	Paper width in inches, or with a unit e.g. "210mm".
`paperHeight`	No	Paper height in inches.
`marginTop`	No	Top margin in inches.
`marginBottom`	No	Bottom margin in inches.
`marginLeft`	No	Left margin in inches.
`marginRight`	No	Right margin in inches.
`scale`	No	Render scale, 0.1–2.0.
`printBackground`	No	Print background graphics/colors.
`preferCssPageSize`	No	Use the page size declared in CSS @page rules.
`nativePageRanges`	No	Page ranges to include, e.g. "1-3,5".
`pdfa`	No	PDF/A conformance level, e.g. "PDF/A-2b". (Pro/Scale/trial only.)
`pdfua`	No	Produce an accessible PDF/UA document.
`userPassword`	No	Password required to open the resulting PDF.
`ownerPassword`	No	Owner password controlling permissions on the resulting PDF.
`save_path`	No	Optional absolute path to also write the PDF to on disk.

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only have openWorldHint=true, so description carries burden. It adds credit cost and return format, but does not disclose side effects like file writing via save_path parameter or rendering environment details. Additional behavioral info is valuable but incomplete.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences with zero waste: action, optional options, cost, output. Front-loaded with purpose. Every sentence adds distinct value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 18 parameters and no output schema, description covers main action, input, output, and cost. Missing side effects (save_path file writing), rendering environment details (JavaScript execution), and timeouts. Adequate but not comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. Description groups parameters as 'optional CSS and layout options', adding minimal meaning beyond schema. No new constraints or format details provided.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses strong verb 'Render' and specific resource 'raw HTML string', output 'PDF'. It clearly distinguishes from siblings: convert_file (likely file-based), convert_markdown (markdown input), and get_account (unrelated).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states 'raw HTML string' implying file-based HTML should use convert_file, but no explicit when-not or alternative mention. Context is clear enough due to sibling tool names, but lacks direct exclusionary guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

convert_markdownConvert Markdown to PDFAInspect

Render a raw Markdown string to a PDF, with optional CSS and layout options. A sensible default stylesheet is applied when no CSS is given. Costs 1 credit on success. Returns the PDF as an embedded resource.

ParametersJSON Schema

Name	Required	Description
`markdown`	Yes	The Markdown content to render.
`css`	No	Optional CSS to style the rendered Markdown (overrides the default stylesheet).
`landscape`	No	Render in landscape orientation. (Pro/Scale/trial only.)
`paperWidth`	No	Paper width in inches, or with a unit e.g. "210mm".
`paperHeight`	No	Paper height in inches.
`marginTop`	No	Top margin in inches.
`marginBottom`	No	Bottom margin in inches.
`marginLeft`	No	Left margin in inches.
`marginRight`	No	Right margin in inches.
`scale`	No	Render scale, 0.1–2.0.
`printBackground`	No	Print background graphics/colors.
`preferCssPageSize`	No	Use the page size declared in CSS @page rules.
`nativePageRanges`	No	Page ranges to include, e.g. "1-3,5".
`pdfa`	No	PDF/A conformance level, e.g. "PDF/A-2b". (Pro/Scale/trial only.)
`pdfua`	No	Produce an accessible PDF/UA document.
`userPassword`	No	Password required to open the resulting PDF.
`ownerPassword`	No	Owner password controlling permissions on the resulting PDF.
`save_path`	No	Optional absolute path to also write the PDF to on disk.

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds transparency beyond annotations by stating the cost (1 credit) and return type (embedded resource), and that a default stylesheet is applied. However, it does not disclose potential side effects (e.g., writing to disk via save_path) or required permissions. Annotations only provide openWorldHint, which is not contradicted, but the description is only partially transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise, consisting of two sentences that front-load the core purpose and key details (defaults, cost, return). Every sentence adds value, with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (18 parameters, no output schema, minimal annotations), the description covers essential purpose and return type but lacks depth on layout options or parameter interactions. It is adequate but not exceptional for guiding an agent through all available features.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the parameters are already well-documented in the schema. The description adds a high-level summary ('optional CSS and layout options') but no new details beyond what the schema provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool renders a raw Markdown string to a PDF with optional CSS/layout options, using specific verbs and resources. It distinguishes itself from siblings like convert_html (HTML to something) and convert_file (file format conversion) by focusing on Markdown input and PDF output.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use this tool (Markdown to PDF) and mentions defaults (default stylesheet) and cost, but does not explicitly state when not to use it or provide alternatives. Context from sibling tools clarifies the niche, but direct guidance is missing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_accountGet FileToPDF account statusA

Read-only

Inspect

Check the FileToPDF API key and return the plan, remaining conversion credits, and subscription status. Free — costs no credits. Use this to verify the connection works.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint and openWorldHint, indicating safe, state-dependent reading. The description adds specific details about what is returned (plan, credits, subscription status) and confirms no cost, consistent with the annotations. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short, clear sentences with no wasted words. Purpose is front-loaded and every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no parameters and no output schema, the description covers the return values and use case. Could mention how the API key is supplied (probably via authentication), but overall sufficient given annotations and sibling context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, so baseline is 4 per guidelines. The description does not need to explain parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool checks the FileToPDF API key and returns plan, credits, and subscription status. It distinguishes itself from sibling conversion tools (convert_file, convert_html, convert_markdown) by specifying it is for status verification and costs no credits.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Use this to verify the connection works' and notes it is free, implying use before conversion tasks. It clearly differentiates from siblings but lacks explicit when-not-to-use or alternative pointers.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

4 tool updatesv0.1.0Jun 9, 2026
- First observedconvert_file
- First observedconvert_html
- First observedconvert_markdown
- First observedget_account

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.1/5.0

Scored 2026-06-09 19:25 across 4 tools

Disambiguation5/5

Each conversion tool targets a distinct input type (URL-based files, raw HTML, raw Markdown), and get_account is separate. No overlap.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (convert_file, convert_html, convert_markdown, get_account).

Tool Count5/5

Four tools is appropriate for a focused PDF conversion server, covering the main conversion methods and account info.

Completeness5/5

The tool surface covers all major conversion paths (URL-based auto-detection, raw HTML, raw Markdown) and account verification, with no obvious gaps.

Maintenance

ActivityInactive

ResponsivenessUnresponsive

Resources

Need Help?

Related Servers

Related MCP Connectors

MintPDF A
io.github.TrendTweekers
Turn HTML or Markdown into a clean, styled PDF and get a download link.
Browser Automation Workplace & Productivity
211
pdfAssistantOAuth
ai.pdfassistant
Convert, merge, compress, OCR, redact, and sign PDFs inside your AI assistant. From pdfAssistant.
Multimedia Processing
1
PdfBroker.io A
io.pdfbroker
Cloud PDF generation from HTML, CSS and XSL-FO, with PDF/A and PDF/UA support.
Developer Tools Workplace & Productivity
21
APICK Convert A
app.apick
File conversion: PDF, DOCX, STT, TTS, watermarking
Multimedia Processing Audio Processing Text-to-Speech
2211

Related MCP Servers

Yakpdf MCP Server
Web Scraping App Automation
BACH-AI-Tools
A
license
B
quality
D
maintenance
Enables PDF generation from URLs or HTML strings through the Yakpdf API, allowing users to convert web content into PDF documents.
Updated 9 months ago (2025-12-08 00:21 UTC)
1
MIT
PDF Manipulation MCP Server
File Systems Developer Tools
fastmcp-me
A
license
B
quality
D
maintenance
Enables PDF manipulation including text, images, annotations, form fields, page operations, and metadata through natural language.
Updated 10 months ago (2025-11-04 09:36 UTC)
16
MIT
1pdf
File Systems
WendongAI
A
license
C
quality
B
maintenance
Enables AI assistants to perform PDF operations like merge, split, compress, convert, encrypt, OCR, and summarize using natural language.
Updated 2 months ago (2026-07-28 12:55 UTC)
98
7 npm
MIT
document-conversion-api
Documentation Access File Systems Data Platforms
nexus-mcp-infra
F
license
Not graded
quality
B
maintenance
Enables conversion between PDF/Office documents and structured JSON, supporting extraction and generation of document content.
Updated 17 days ago (2026-08-31 23:08 UTC)
-

FileToPDF MCP server

Tools

Quick start (local / stdio)

Hosted / remote (Streamable HTTP) — no install

Develop & test

Links

License

Available Tools

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers