PDF Export for AI Agents
Official
PDF Export for AI Agents
Well-designed PDFs from a single prompt. Describe what you need, get a professional document.
Powered by PDFCrowd. Learn more →
Example
Analyze this project and create a comprehensive architecture overview PDF.
Include component diagrams and data flow. Save to architecture-overview.pdf
Related MCP server: Resume Generator MCP Server
Configuration
Prerequisites: Node.js 18 or later.
Claude Code
Option A — Install as a plugin (Recommended):
/plugin marketplace add pdfcrowd/pdfcrowd-mcp-pdf-export
/plugin install pdfcrowd-export-pdf@pdfcrowdOption B — Register the MCP server:
claude mcp add --scope user pdfcrowd-export-pdf -- npx -y pdfcrowd-mcp-pdf-exportOr add the equivalent JSON to ~/.claude.json (user scope) or .mcp.json (project scope):
{
"mcpServers": {
"pdfcrowd-export-pdf": {
"command": "npx",
"args": ["-y", "pdfcrowd-mcp-pdf-export"]
}
}
}Codex CLI
codex mcp add pdfcrowd-export-pdf -- npx -y pdfcrowd-mcp-pdf-exportOr add manually to ~/.codex/config.toml:
[mcp_servers.pdfcrowd-export-pdf]
command = "npx"
args = ["-y", "pdfcrowd-mcp-pdf-export"]Gemini CLI
gemini mcp add -s user pdfcrowd-export-pdf npx -y pdfcrowd-mcp-pdf-exportOr add manually to ~/.gemini/settings.json:
{
"mcpServers": {
"pdfcrowd-export-pdf": {
"command": "npx",
"args": ["-y", "pdfcrowd-mcp-pdf-export"]
}
}
}Notes
Restart your CLI after configuration to load the server
Personal Credentials
Get started right away — no credentials or signup needed. Output includes a watermark. For watermark-free PDFs, sign up for personal credentials.
Personal credentials can be set in:
Config file
~/.pdfcrowd-mcp:PDFCROWD_USERNAME=your_username PDFCROWD_API_KEY=your_api_keyEnvironment variables
PDFCROWD_USERNAMEandPDFCROWD_API_KEY.
Privacy
Your source code never leaves your machine — only the rendered document is sent to PDFCrowd for PDF conversion.
License
Available Tools
2 toolspdfcrowd_create_pdfCreate PDFAIdempotent
Export any content (including charts) to PDF. If input isn't HTML, create a well-designed layout first. IMPORTANT: Call pdfcrowd_info(topic: "parameters") to get the full input schema. IMPORTANT: Before creating HTML, first call pdfcrowd_info(topic: "html_layout") to get the layout guidelines. Do NOT pass PDFCrowd API parameters - this tool has its own schema.
On error: Read the error message carefully and follow its guidance. Report configuration issues to the user instead of trying other PDF tools.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide hints (readOnlyHint: false, destructiveHint: false, etc.), but the description adds valuable context beyond these: it explains that non-HTML input requires layout creation first, details error-handling behavior ('Read the error message carefully'), and specifies not to use other PDF tools on configuration issues. This enhances transparency without contradicting annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core purpose but includes multiple IMPORTANT notes and error-handling instructions that, while useful, make it somewhat verbose. Each sentence adds value (e.g., layout guidelines, error guidance), but it could be more streamlined for better conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (involving HTML layout and external schema references) and lack of output schema, the description is reasonably complete: it covers purpose, prerequisites, error handling, and references to additional info. However, it doesn't detail output format or success behavior, leaving some gaps in contextual understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0 parameters with 100% coverage, so the description doesn't need to explain parameters. It mentions calling 'pdfcrowd_info' to get the full input schema, which implies parameters exist but are documented elsewhere. This meets the baseline of 3 for high schema coverage without adding parameter details.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Export any content (including charts) to PDF' with a specific verb ('Export') and resource ('PDF'). It distinguishes from the sibling tool 'pdfcrowd_info' by focusing on PDF creation rather than information retrieval. However, it doesn't explicitly differentiate from other potential PDF creation tools beyond mentioning not to use other PDF tools on errors.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when and how to use this tool: it instructs to call 'pdfcrowd_info' for parameters and layout guidelines before use, specifies not to pass PDFCrowd API parameters, and gives clear error-handling instructions ('Report configuration issues to the user instead of trying other PDF tools'). This covers when to use alternatives and prerequisites effectively.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
pdfcrowd_infoPDF Export InfoC
Get usage tips and upgrade info for PDF Export
| Name | Required | Description | Default |
|---|---|---|---|
| topic | No | Optional topic for specific guidance. Available: html_layout, mermaid_diagrams, local_assets, parameters |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes a read-only informational operation ('Get usage tips and upgrade info'), which implies it's safe and non-destructive, but it doesn't specify any behavioral traits like authentication needs, rate limits, or what the output format might be (e.g., text, structured data). This leaves significant gaps for an agent to understand how to interact with it effectively.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise and front-loaded, consisting of a single, clear sentence that directly states the tool's purpose without any wasted words. Every part of the sentence earns its place by conveying essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (a simple informational tool with one optional parameter) and the lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., the format or content of the 'usage tips and upgrade info'), which is critical for an agent to use it correctly. The schema covers the input well, but the output remains unspecified, making the overall context insufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the 'topic' parameter fully documented in the schema (including optional nature and available values). The description doesn't add any meaning beyond what the schema provides, as it doesn't mention parameters at all. With high schema coverage, the baseline score of 3 is appropriate, as the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with a specific verb ('Get') and resource ('usage tips and upgrade info for PDF Export'), making it immediately understandable. However, it doesn't explicitly differentiate from its sibling tool 'pdfcrowd_create_pdf' (which presumably creates PDFs rather than providing information), so it misses the highest score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention the sibling tool or any other context for usage, leaving the agent to infer based on the tool name and description alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
The two tools have clearly distinct purposes: pdfcrowd_create_pdf is for creating PDFs from content, while pdfcrowd_info is for retrieving usage information and guidelines. There is no overlap in functionality, making it easy for an agent to choose the right tool for each task.
Both tools follow a consistent naming pattern with the prefix 'pdfcrowd_' followed by a descriptive verb_noun combination (create_pdf and info). This consistency makes the tool set predictable and easy to understand at a glance.
With only two tools, the server feels thin for its purpose of PDF export for AI agents. While the core PDF creation tool is present, the lack of supporting tools (e.g., for managing PDFs, handling errors beyond info, or advanced formatting) limits functionality and may require agents to work around gaps.
The tool set is severely incomplete for PDF export operations. It includes creation and info retrieval but lacks essential tools for updating, deleting, or listing PDFs, as well as tools for handling common PDF tasks like merging or splitting. This will likely cause agent failures in more complex workflows.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Turn a description into a shareable, editable PDF — invoices, certificates, reports, resumes.
Generate and read PDFs for AI agents: a generate_pdf and a read_pdf tool, priced per document.
Generate PDFs from templates via AI chat. Works with Claude, ChatGPT, Cursor, and any MCP client.
Turn any PDF into structured JSON via AI + OCR: invoices, bank statements, contracts.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to generate professional PDF documents from markdown content with advanced typography, syntax highlighting, math equations, dark mode, and customizable styling options.MIT
- AlicenseAqualityCmaintenanceGenerates professional PDF resumes using LaTeX templates through natural language descriptions. Supports 9 professional templates, AI-powered resume tailoring, and organized folder management for job applications.423MIT
- AlicenseAqualityCmaintenanceGenerate professional PDFs from Claude, Cursor, and other AI tools. Create invoices, contracts, reports, and certificates from templates or inline HTML markup.7591MIT
- AlicenseAqualityBmaintenanceTurn markdown into designed PDFs with cover page, table of contents, and code blocks that hold across pages. One command from Claude Desktop, Claude Code, Cursor, Cline, Zed, or any MCP-capable client.2631MIT
Appeared in Searches
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/pdfcrowd/pdfcrowd-mcp-pdf-export'
If you have feedback or need assistance with the MCP directory API, please join our Discord server