English Français العربية

PDF To Text

Official registry Productivity

Extracts PDF text locally, with macOS PDFKit and Vision OCR fallbacks and optional AI retry.

Source code

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

NPM package @jim-panse/pdf-to-text-mcp
Claude Code 
claude mcp add pdf-to-text -e 'PDF_TO_TEXT_MCP_ROOT=<PDF_TO_TEXT_MCP_ROOT>' -e 'OPENAI_API_KEY=<your openai_api_key>' -e 'OPENAI_MODEL=<OPENAI_MODEL>' -e 'AI_MAX_OUTPUT_TOKENS=32000' -e 'MAX_PARALLEL_EXTRACTIONS=<MAX_PARALLEL_EXTRACTIONS>' -e 'EXTRACTION_QUEUE_CAPACITY=10' -e 'EXTRACTION_QUEUE_WAIT_MS=60000' -e 'WRITE_TEXT=false' -- npx -y @jim-panse/pdf-to-text-mcp@0.7.0
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "pdf-to-text": {
            "command": "npx",
            "args": [
                "-y",
                "@jim-panse/pdf-to-text-mcp@0.7.0"
            ],
            "env": {
                "PDF_TO_TEXT_MCP_ROOT": "<PDF_TO_TEXT_MCP_ROOT>",
                "OPENAI_API_KEY": "<your openai_api_key>",
                "OPENAI_MODEL": "<OPENAI_MODEL>",
                "AI_MAX_OUTPUT_TOKENS": "32000",
                "MAX_PARALLEL_EXTRACTIONS": "<MAX_PARALLEL_EXTRACTIONS>",
                "EXTRACTION_QUEUE_CAPACITY": "10",
                "EXTRACTION_QUEUE_WAIT_MS": "60000",
                "WRITE_TEXT": "false"
            }
        }
    }
}

Environment variables

  • PDF_TO_TEXT_MCP_ROOT required Required existing directory that defines the root-relative filesystem namespace for PDF input and derived text output.
  • OPENAI_API_KEY secret Optional secret. Enables one AI extraction retry when local extraction is inadequate; omit for local-only operation.
  • OPENAI_MODEL Optional OpenAI model used only for AI retry. Defaults to gpt-5.4-mini.
  • AI_MAX_OUTPUT_TOKENS Optional cap for all AI-generated output tokens, including non-visible reasoning tokens. Integer minimum 800; defaults to 32000.
  • MAX_PARALLEL_EXTRACTIONS Integer concurrency limit from 1 to 32. Defaults to min(os.availableParallelism(), 4).
  • EXTRACTION_QUEUE_CAPACITY Integer maximum waiting requests from 0 to 100; zero disables waiting.
  • EXTRACTION_QUEUE_WAIT_MS Maximum queue wait in milliseconds, integer 1 through 2147483647. Does not limit active work.
  • WRITE_TEXT Optionally save successful extraction text beside the source PDF.

Frequently asked questions

What is PDF To Text?

Extracts PDF text locally, with macOS PDFKit and Vision OCR fallbacks and optional AI retry.

How do I install PDF To Text?

It runs on your machine. In Claude Code: claude mcp add pdf-to-text -e 'PDF_TO_TEXT_MCP_ROOT=<PDF_TO_TEXT_MCP_ROOT>' -e 'OPENAI_API_KEY=<your openai_api_key>' -e 'OPENAI_MODEL=<OPENAI_MODEL>' -e 'AI_MAX_OUTPUT_TOKENS=32000' -e 'MAX_PARALLEL_EXTRACTIONS=<MAX_PARALLEL_EXTRACTIONS>' -e 'EXTRACTION_QUEUE_CAPACITY=10' -e 'EXTRACTION_QUEUE_WAIT_MS=60000' -e 'WRITE_TEXT=false' -- npx -y @jim-panse/pdf-to-text-mcp@0.7.0. For other clients, paste the JSON configuration from this page into their MCP settings.

Does PDF To Text need an API key?

Yes. It expects PDF_TO_TEXT_MCP_ROOT, OPENAI_API_KEY, which you set in its configuration.

Is PDF To Text open source?

Its code is public on GitHub, but the repository does not declare a standard license.

Who maintains PDF To Text?

It is published by Jim-Panse. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.