OCR.space for AI agents
OCR.space is a text-extraction API that pulls readable text out of images and PDFs and returns it as JSON. Developers use it for lightweight OCR without running their own recognition engine. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in OCR.space.
Extract text from an uploaded PDF
Convert a scanned PDF into machine-readable text for search or downstream processing.
Pull text from an image URL
Extract text directly from a hosted image link without downloading the file first.
Check conversion usage read-only
Review conversion statistics to track how much OCR volume has been used this period.
3 OCR.space actions, graded by risk.
Every OCR.space action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
2Look things up. Allowed by default.
- ocr_space.get_conversionsGet Conversion Statistics
- ocr_space.parse_image_urlExtract Text from Image URL (GET)
write
1Create and change things. Allow, or ask the user first.
- ocr_space.ocr_parse_image_postExtract Text from Image/PDF (OCR)
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
OCR.space in three steps.
- 01Your users connect OCR.spaceThey add their OCR.space api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “extract Text from Image/PDF (OCR)” can wait for the user to approve.
- 03Any agent can actYour agent calls OCR.space through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('ocr_space', { read: 'allow', write: 'ask', // ocr_parse_image_post destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How OCR.space connects.
Users add their OCR.space api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same OCR.space connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use OCR.space from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
OCR.space and Arc0, answered.
Can I use OCR.space with Claude, ChatGPT or Cursor?
Yes. Connect OCR.space to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the OCR.space actions you allow.
How do users connect OCR.space?
Users add their OCR.space api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which OCR.space actions can my agent take?
3 in total: 2 read, 1 write and 0 destructive, such as “extract Text from Image/PDF (OCR)”. Your policies decide which of them each agent may call.
Can I make my agent read-only in OCR.space?
Yes. Allow read actions and deny writes in the OCR.space policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call OCR.space too?
Yes. The same OCR.space connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug OCR.space into your agent.
Your users connect OCR.space once, under your brand. Your agent gets 3 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan