Iteration Layer

Your agents need tools that work like they think

AI agents orchestrate multi-step workflows: read a document, process images, generate a report. But most APIs weren't built for machine consumption — poor structured output, no tool-use metadata, ambiguous errors. Ours were.

No credit card required — start with free trial credits

Zero data retention · GDPR Made & hosted in the EU $60 free trial credits No credit card required 14-day money-back guarantee

One output feeds the next

APIs that cover every step of your content pipeline — ingestion, transformation, and generation. One key, one credit pool, and structured JSON responses designed to chain together.

Fits into your existing stack

Native SDKs for Node, Python, and Go. OpenAPI spec for everything else. MCP server for AI agents and Claude Code skills. n8n community node for visual workflows.

Mix and match freely

Extract data from a document, generate visuals from the results, then compile everything into a finished report. Mix, match, and build your own pipeline.

You're dealing with this every day

Here's what changes when you stop juggling tools and start building pipelines.

Unstructured outputs

Most document and image APIs return unstructured blobs, have ambiguous error messages, and lack the typed schemas that agents need to function reliably without human oversight.

Structured, typed I/O

JSON schemas in, structured data out. Every response includes typed fields that agents can parse and pipe into the next step. No scraping HTML or guessing formats.

One vendor per capability

Your agent needs to read documents, process images, and generate files — but each capability comes from a different service with different auth, different conventions, and different failure modes.

Every tool, one server

Your agent doesn't need to juggle multiple APIs. It sees one coherent set of capabilities — extraction, transformation, generation — that compose naturally.

No MCP for content

The MCP ecosystem is growing fast, but finding reliable, well-documented servers for content processing is still a challenge. Most are wrappers around APIs that weren't designed for agents.

Native MCP server

All APIs exposed as composable tools through a single MCP server. Claude, Cursor, Windsurf, and custom frameworks can discover and use them without custom integration code.

Real-world pipelines, ready to ship

Each recipe chains multiple APIs into a complete workflow. Pick one, tweak it, and deploy — or use it as a starting point for your own pipeline.

Official SDKs for every major language

Install the SDK, set your API key, and start chaining requests. Full type safety, automatic retries, and idiomatic error handling included.

Your data stays in the EU

Your data is processed on EU servers and never stored beyond temporary logs. Zero retention, GDPR-compliant by design, with a Data Processing Agreement available for every customer. Learn more about our security practices .

No data storage, no model training

We don't store your files or processing results, and your data is never used to train or improve AI models. Logs are automatically deleted after 90 days.

EU-hosted infrastructure

All processing runs on servers located in the European Union. Your data never leaves the EU.

GDPR-compliant by design

Full compliance with EU data protection regulations. Data Processing Agreement available for all customers.

Pricing

Start with free trial credits. No credit card required.

I need...

document pages extracted
document pages converted to markdown
images transformed
images generated
documents generated
sheets generated

Real-world examples

All APIs included Free trial credits per API Project-based budget caps Auto overage billing

Solving real problems, step by step

Vendor sprawl, GDPR headaches, broken pipelines — we wrote about the problems you're facing and how to fix them.

Build your first workflow in minutes

Chain our APIs together and ship a complete pipeline before lunch. Free trial credits included — no credit card required.

Frequently asked questions

How do I connect the MCP server to my agent?
Install via npx or configure it in your MCP client's settings. The server exposes all APIs as tools with full JSON schemas. Claude Desktop, Cursor, and Windsurf support it natively. See the MCP docs.
Can agents chain multiple operations?
Yes — that's the core design. An agent can extract data from a PDF, generate a summary document from the results, and create a thumbnail image, all through the same MCP server.
What content types can agents process?
Documents (PDF, DOCX, XLSX, CSV), images (PNG, JPEG, WebP, HEIF), audio, and web pages. Agents can extract data, transform images, and generate PDFs, spreadsheets, and images — all through the same MCP server.
What response format do the APIs return?
Every API returns structured JSON with typed fields. Document Extraction returns field-level data with confidence scores. Image Generation returns base64 or URLs. All responses follow consistent schemas your agent can parse without guesswork.
Do you have Claude Code skills?
Yes. We publish Claude Code skills that wrap our APIs into ready-to-use agent capabilities. See the AI Integration docs.
Do you provide an OpenAPI spec?
Yes. A full OpenAPI 3.1 specification is available at our gateway endpoint. Use it for code generation, IDE integration, or to build custom agent tool definitions.
How do agents handle errors?
All errors return structured JSON with a consistent format — error type, message, and HTTP status. No HTML error pages or ambiguous responses. Credits are refunded on server errors automatically. See Errors.
Is there rate limiting?
Yes, but generous. Rate limits are per API key and designed for production workloads. If your agent needs higher limits, contact us — we can adjust per account. See Rate Limits.