# Mighty Docs

> Mighty is an input trust layer for products that process user text, files, images, OCR output, model output, and workflow data.

Use these docs to add Mighty to real products. The core API is `POST /v1/scan`.

## Start Here

- [Docs Home](https://trymighty.ai/docs)
- [Quickstart](https://trymighty.ai/docs/quickstart)
- [Mighty Platform](https://trymighty.ai/docs/platform)
- [Use Cases](https://trymighty.ai/docs/use-cases)
- [FAQ](https://trymighty.ai/docs/faq)
- [How Mighty Works](https://trymighty.ai/docs/concepts/how-mighty-works)
- [Modalities And Attacks](https://trymighty.ai/docs/concepts/modalities-attacks)
- [Modes And Tolerance](https://trymighty.ai/docs/concepts/modes-tolerance)
- [Choose Scan Settings](https://trymighty.ai/docs/concepts/configs)
- [Glossary](https://trymighty.ai/docs/concepts/glossary)
- [Drift](https://trymighty.ai/docs/concepts/drift)
- [Integration Guides](https://trymighty.ai/docs/integrate)
- [Multimodal Support](https://trymighty.ai/docs/integrate/multimodal-support)
- [Framework Integration Map](https://trymighty.ai/docs/frameworks)
- [Sessions And Scan Groups](https://trymighty.ai/docs/concepts/sessions)
- [Billing, SCU, And Limits](https://trymighty.ai/docs/concepts/billing-scu)
- [OpenAPI](https://trymighty.ai/openapi/mighty-api.yaml)
- [Full Markdown](https://trymighty.ai/llms-full.txt)

## Product Pages

- [Mighty Home](https://trymighty.ai/): Detect AI document fraud before people or automation act on a customer file.
- [Product](https://trymighty.ai/product): One scan for any document, photo, or extracted text, returning an auditable allow, review, or block decision.
- [Use Cases](https://trymighty.ai/use-cases): Where AI-altered content enters real workflows — claim packets, estimates, damage photos, invoices, and OCR output.
- [Lending](https://trymighty.ai/lending): Catch AI-altered paystubs, W-2s, bank statements, and tax returns before you fund a loan.
- [Claims](https://trymighty.ai/claims): Screen AI-manipulated damage photos, repair estimates, and invoices at first notice of loss, before the payout.
- [Why Mighty](https://trymighty.ai/why-mighty): Why manual review can no longer catch AI-generated document forgery.
- [Pricing](https://trymighty.ai/pricing): Usage-based scan pricing, scoped with you on a call.
- [Security](https://trymighty.ai/security): How Mighty handles your data, retention, and responsible disclosure.

## Pages

- [Mighty Docs](https://trymighty.ai/docs): Add Mighty to chat apps, upload flows, OCR pipelines, AI fraud review, and agentic systems.
- [5-Minute Quickstart](https://trymighty.ai/docs/quickstart): Run your first Mighty scan in curl, TypeScript, Python, or Go. See what ALLOW, WARN, and BLOCK actually look like.
- [Mighty Platform](https://trymighty.ai/docs/platform): Understand API keys, permissions, content logging modes, billing status, and safe key handling in the Mighty dashboard.
- [Use Cases](https://trymighty.ai/docs/use-cases): See where Mighty creates value in chat, uploads, OCR, claims, invoices, agents, batch intake, and AI fraud review.
- [FAQ](https://trymighty.ai/docs/faq): Clear answers about what Mighty is, what it is not, and how to use it before the AI layer.
- [How Mighty Works](https://trymighty.ai/docs/concepts/how-mighty-works): Understand the scan pipeline, what Mighty inspects, what it returns, and where your app routes risk.
- [Modalities And Attacks](https://trymighty.ai/docs/concepts/modalities-attacks): Understand what Mighty checks across text, images, documents, OCR output, model output, and closed beta audio.
- [Modes And Tolerance](https://trymighty.ai/docs/concepts/modes-tolerance): Choose fast, secure, or comprehensive mode, then set tolerance with profile, data sensitivity, and routing policy.
- [Choose Scan Settings](https://trymighty.ai/docs/concepts/configs): Pick content type, phase, mode, focus, profile, and data sensitivity from real product examples.
- [Glossary](https://trymighty.ai/docs/concepts/glossary): Plain-language definitions for Mighty scan, image evidence, billing, and prompt-safety terms.
- [Sessions And Scan Groups](https://trymighty.ai/docs/concepts/sessions): Use session IDs, scan groups, and request IDs to connect multistep scans across chats, files, OCR, output, and review.
- [Drift](https://trymighty.ai/docs/concepts/drift): Handle changes in inputs, models, policies, evidence chains, and attacker behavior over time.
- [Billing, SCU, And Limits](https://trymighty.ai/docs/concepts/billing-scu): Understand Security Compute Units, modality billing, included allowance, overage, tier caps, and file limits.
- [Integration Guides](https://trymighty.ai/docs/integrate): Choose the Mighty integration guide for text, OCR, uploads, images, model output, async scans, and errors.
- [Multimodal Support](https://trymighty.ai/docs/integrate/multimodal-support): Choose the right Mighty settings for text, images, PDFs, documents, OCR output, model output, and PII-heavy workflows.
- [Scan Text And OCR Output](https://trymighty.ai/docs/integrate/text-ocr): Use Mighty on plain text, extracted text, OCR output, and IDP fields before downstream automation trusts them.
- [Scan File Uploads](https://trymighty.ai/docs/integrate/file-uploads): Scan uploaded PDFs, images, and documents before storage, OCR, AI extraction, or workflow routing.
- [Damage Photo AI Fraud Review](https://trymighty.ai/docs/integrate/images-ai-fraud): Scan images for risk and authenticity signals before claims, repair, insurance, or review workflows trust them.
- [Scan Model Output](https://trymighty.ai/docs/integrate/model-output): Check generated model output before users, workflows, or agents act on it.
- [Async Deep Scans](https://trymighty.ai/docs/integrate/async-webhooks): Use async scans, polling, and webhooks for deep image and PDF review.
- [Error Handling](https://trymighty.ai/docs/integrate/errors): Handle common Mighty errors, billing states, limits, rate limits, and async states.
- [Framework Integration Map](https://trymighty.ai/docs/frameworks): Choose the right Mighty pattern for chat, uploads, backend APIs, serverless routes, and agent frameworks.
- [Vercel AI SDK Chat Guardrail](https://trymighty.ai/docs/frameworks/vercel-ai-sdk): Wrap Mighty as a wrapLanguageModel middleware for AI SDK 5+. One wrap, every model call screened — input + output, streaming + buffered, with optional AI Gateway routing.
- [Next.js Upload Guardrail](https://trymighty.ai/docs/frameworks/next-file-upload): Scan browser uploads in a Next.js Route Handler before storage, OCR, extraction, or review.
- [Backend API Helpers](https://trymighty.ai/docs/frameworks/node-python): Use these server-side helper patterns when your backend is Node, Python, Express, FastAPI, Flask, Django, or a custom API.
- [Workflow Playbooks](https://trymighty.ai/docs/workflows): Pick the product workflow you are building, then copy the Mighty scan plan for that workflow.
- [POST /v1/scan](https://trymighty.ai/docs/api-reference/v1-scan): Request fields, response fields, errors, polling, and OpenAPI download for the public scan API.
- [Use With AI](https://trymighty.ai/docs/ai): Copy prompts, Markdown exports, llms.txt, and integration instructions for AI coding agents.
- [Document Processing Pipeline](https://trymighty.ai/docs/frameworks/document-pipeline): Multi-stage trust boundaries for claim packets, invoices, and signed forms. One scan_group_id flows through upload → file scan → OCR → text scan → LLM enrichment → output scan → DB write. Forged-invoice walkthrough included.
- [LangChain + LangGraph Guardrail](https://trymighty.ai/docs/frameworks/langchain-langgraph): Drop Mighty in as an AgentMiddleware on create_agent for the modern path, or as a guardrail node in raw LangGraph for the advanced path. RAG poisoning, tool-output scanning, and PII redaction in one stack.

## Guidance For AI Coding Agents

When implementing Mighty, read the relevant guide first, then use the request examples and routing logic exactly. Store the API key in `MIGHTY_API_KEY`. Do not expose it to the browser.