OCR.space MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@OCR.space MCP Server Extract text from https://example.com/document.png"
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.
OCR.space MCP Server
Python MCP server for OCR.space - extract text from images and PDFs using OCR.
Features
Six comprehensive tools:
ocr_file- Extract text from local images/PDFsocr_url- Extract text from images/PDFs at URLsocr_auto- Smart OCR that auto-handles oversized filessplit_pdf- Split large PDFs into API-compatible chunkslist_languages- Show supported OCR languagescheck_tier_status- Verify API configuration
Automatic oversized file handling:
PDFs too large? Automatically split by pages, OCR each chunk, join results
Images too large? Automatically compress while preserving quality
Dual-tier support:
Free tier: 1 MB limit, US servers
PRO tier: 5 MB limit, EU endpoint for GDPR compliance
Full API parameter support:
26+ languages including auto-detection
Two OCR engines (optimized for different use cases)
Table optimization mode
Auto-rotation detection
Searchable PDF generation
Save results as TXT or JSON
Related MCP server: EasyOCR MCP Server
Installation
# With uv (recommended)
uv sync
# With pip
pip install -e .Configuration
API Keys
Get your free API key at ocr.space/ocrapi/freekey.
For PRO features (larger files, EU endpoint), sign up at ocr.space/ocrapi.
Environment Variables
Copy .envrc.example to .envrc and configure:
# Required: Free tier API key
export OCR_SPACE_API_KEY="your-free-api-key"
# Optional: PRO tier for GDPR-compliant EU processing
export OCR_SPACE_PRO_API_KEY="your-pro-api-key"
export OCR_SPACE_PRO_ENDPOINT="https://eu.api.ocr.space/parse/image"Then enable with direnv allow.
Claude Code / MCP Config
Add to .mcp.json:
{
"mcpServers": {
"ocr-space": {
"command": "uv",
"args": ["run", "--project", "/path/to/ocr-space-mcp", "ocr-space-mcp"],
"env": {
"OCR_SPACE_API_KEY": "${OCR_SPACE_API_KEY}",
"OCR_SPACE_PRO_API_KEY": "${OCR_SPACE_PRO_API_KEY}",
"OCR_SPACE_PRO_ENDPOINT": "${OCR_SPACE_PRO_ENDPOINT}"
}
}
}
}OpenCode Config
Add to opencode.json:
{
"mcp": {
"ocr-space": {
"command": "uv",
"args": ["run", "--project", "/path/to/ocr-space-mcp", "ocr-space-mcp"],
"env": {
"OCR_SPACE_API_KEY": "${OCR_SPACE_API_KEY}",
"OCR_SPACE_PRO_API_KEY": "${OCR_SPACE_PRO_API_KEY}",
"OCR_SPACE_PRO_ENDPOINT": "${OCR_SPACE_PRO_ENDPOINT}"
}
}
}
}Usage
Check Configuration
Check my OCR.space tier statusOCR a Local File
Extract text from /path/to/document.pdfOCR this image using the PRO tier: /path/to/scan.pngParameters:
Parameter | Description | Default |
| Path to image/PDF (required) | - |
|
|
|
| OCR language code |
|
| 1 (fast) or 2 (accurate) | 1 |
| Save result to file | - |
|
|
|
| Auto-rotate image |
|
| Upscale low-res images |
|
| Optimize for tables |
|
| Generate searchable PDF |
|
OCR from URL
Extract text from https://example.com/document.pngSmart OCR for Large Files (ocr_auto)
The ocr_auto tool automatically handles files that exceed the API size limits:
OCR this large document: /path/to/big-scan.pdfHow it works:
PDFs: Splits into chunks by page, OCRs each chunk, joins results
Images: Compresses (quality + resize) until under limit, then OCRs
Parameters: Same as ocr_file, but no size limit errors!
Split PDF Only
If you just want to split a large PDF without OCR:
Split /path/to/large.pdf for free tier processingCreates multiple smaller PDF files in a temp directory (or specify output_dir).
List Languages
What OCR languages are supported?Supported languages: Arabic, Bulgarian, Chinese (Simplified/Traditional), Croatian, Czech, Danish, Dutch, English, Finnish, French, German, Greek, Hungarian, Italian, Japanese, Korean, Polish, Portuguese, Russian, Slovenian, Spanish, Swedish, Thai, Turkish, Ukrainian, Vietnamese.
Use language=auto with Engine 2 for automatic language detection.
Tier Comparison
Feature | Free | PRO |
File size limit | 1 MB | 5 MB |
Server location | US only | EU available |
Rate limit | 500/day | Unlimited |
GDPR compliance | No | Yes (EU endpoint) |
Price | Free | $30/month |
OCR Engines
Engine | Best For |
Engine 1 | Faster processing, Asian languages, large images |
Engine 2 | Auto-language detection, special characters, rotated text |
Development
# Install with dev dependencies
uv sync --extra dev
# Run linter
uv run ruff check .
# Format code
uv run ruff format .
# Run tests
uv run pytest -v
# Run tests with coverage
uv run pytest --cov=ocr_space_mcp --cov-report=term-missingLicense
MIT - see LICENSE
Links
Available Tools
6 toolscheck_tier_statusA
Check which API tiers are configured and available. Shows which environment variables are set.
Inputs: no named parameters.
list_languagesA
List all supported OCR languages with their codes.
Inputs: no named parameters.
ocr_autoA
Smart OCR that automatically handles oversized files. For PDFs: splits into chunks, OCRs each, and joins results. For images: compresses to fit within size limit before OCR. Use this when you don't know if the file exceeds the size limit.
Inputs: file_path (required), tier, language, ocr_engine, +2 more.
ocr_fileA
Extract text from a local image or PDF file using OCR.space API. Supports PNG, JPG, GIF, BMP, TIFF, PDF. Free tier: max 1 MB. PRO tier: max 5 MB (EU endpoint for GDPR). Optionally saves result to txt or json file.
Inputs: file_path (required), tier, scale, is_table, +7 more.
ocr_urlA
Extract text from an image or PDF at a URL using OCR.space API. The URL must be publicly accessible. Free tier: max 1 MB. PRO tier: max 5 MB.
Inputs: url (required), tier, scale, is_table, +5 more.
split_pdfA
Split a large PDF into smaller chunks that fit within API size limits. Useful for processing PDFs that exceed the 1 MB (free) or 5 MB (pro) limit. Each chunk contains as many pages as possible while staying under the limit.
Inputs: file_path (required), tier, output_dir.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a distinct purpose: URL-based OCR, file-based OCR, auto-handling of oversized files, PDF splitting, language listing, and tier status check. There is no overlap between these operations.
All tool names follow a consistent snake_case verb_noun pattern (e.g., ocr_url, split_pdf, list_languages). The 'ocr_' prefix for the three OCR variations and clear verbs for helpers make the set easy to predict.
With 6 tools, the server is well-scoped: three OCR methods, one PDF utility, and two informational tools. This is neither too sparse nor overloaded for the domain.
The toolset covers the core OCR lifecycle end-to-end: extracting from URL or file, handling oversized inputs via auto-splitting/compression, splitting PDFs manually, and providing necessary supporting info (languages, tier status). No obvious gaps remain.
Maintenance
Related MCP Connectors
OCR.space MCP — wraps the OCR.space API (ocr.space) for image/PDF → text OCR.
Screenshots, PDFs, image editing, QR codes, email validation and more through one hosted MCP server.
Hosted MCP server: convert PDFs to clean, LLM-ready Markdown with tables, formulas and OCR.
MCP server for detecting and redacting PII (Personally Identifiable Information) in PDF documents.
Related MCP Servers
- FlicenseCqualityDmaintenanceAn MCP server that provides a tool to extract text content from local PDF files, supporting both standard PDF reading and OCR capabilities with optional page selection.133-
- AlicenseNot gradedqualityDmaintenanceAn MCP server that provides OCR capabilities using the EasyOCR library, supporting over 80 languages and GPU acceleration. It enables processing images from base64 strings, local files, or URLs with options for text-only or detailed coordinate and confidence output.2Apache 2.0
- AlicenseNot gradedqualityCmaintenanceOCR.space MCP server that enables image and PDF text extraction via the OCR.space API.92 npmMIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server wrapping PaddleOCR to provide OCR text recognition for Chinese, English, Japanese, and Korean languages, supporting images from local paths, URLs, and base64 data.MIT