Summary
Connects Claude to the space-ocr API for structured OCR that anchors LLM extractions to real Google Vision API character bounding boxes instead of hallucinated coordinates. Exposes two tools: ocr_extract for pulling structured fields from document images (receipts, invoices, passports, or custom schemas) and list_templates for browsing the nine built-in document types. Accepts URLs, local paths, or base64 images. Reach for this when your agent needs to auto-fill forms, build verification UIs, or reconcile accounting data and the pixel-level position of each character actually matters. Requires a space-ocr API key and runs via npx with flat ¥10 per-call pricing.
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →space-ocr-mcp
MCP (Model Context Protocol) server for space-ocr — structured OCR with verified per-character bounding boxes.
Why
Unlike calling Gemini/GPT-4V directly, space-ocr re-anchors LLM output to real Google Vision API symbols, so bounding boxes are not hallucinated. AI agents that act on the extracted data (auto-fill, verification UI, accounting reconciliation) can trust the coordinates.
Tools
ocr_extract— Extract structured fields from a document image. Passtemplate_idfor built-in document types orfieldsfor custom schemas.list_templates— List built-in document templates (receipt,invoice,purchase_order,delivery,quote,bankbook,resident_card,driver_license,passport).
Install & run
npx -y space-ocr-mcp
Set SPACE_OCR_API_KEY (issue one at space-ocr.com → Settings → API Keys).
Claude Desktop config
~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"space-ocr": {
"command": "npx",
"args": ["-y", "space-ocr-mcp"],
"env": { "SPACE_OCR_API_KEY": "YOUR_API_KEY" }
}
}
}
Restart Claude Desktop. You should see the space-ocr tools available.
Cursor / Windsurf / other MCP clients
Use the same command / args / env pattern in their MCP configuration UI.
Image inputs
ocr_extract accepts:
- A public URL (
https://...) - A local file path (
/path/to/file.jpg— auto base64-encoded) - A base64 string
- A
data:image/...;base64,...URI
Pricing
¥10 per call (flat), billed against the same Charge Amount balance as the REST API. Failed calls are auto-refunded. Out-of-balance returns an error with no charge.
License
MIT
Featured
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Configuration
SPACE_OCR_API_KEY*secretAPI key for space-ocr. Issue at https://space-ocr.com → Settings → API Keys.