# Cradl AI MCP

Vendor: Cradl AI  
Category: docs  
Auth: OAUTH2  
Composio slug: `cradl_ai`

Cradl AI is an API-first platform for building and operating AI-powered document extraction workflows.

## Tools

- **Download File** — Download document, OCR, annotation, prediction, or run-variable content from a Cradl AI file URL returned by another Cradl AI tool.
- **Get Agent Run** — Get the current state and outputs of one Cradl AI agent run. Poll this read-only tool until the run reaches a terminal status; it does not itself consume page quota.
- **Get Document** — Get metadata, processing links, and annotations for one Cradl AI document by ID. This read does not consume page quota.
- **Get Prediction** — Get one extracted prediction, including its status, fields, errors, and downloadable output references. This read does not consume page quota.
- **List Agent Runs** — List processing runs for an agent, optionally filtered by status or creation/update time. Use this to discover recent extraction jobs and their run IDs.
- **List Agents** — List document-processing agents available to the connected Cradl AI workspace. Use an agent ID from this result to start an extraction run.
- **List Documents** — List documents in the connected Cradl AI workspace and discover document IDs and content/output file URLs.
- **List Predictions** — List extracted predictions, optionally filtered by model, and discover prediction IDs and output file URLs.
- **Process Document** — Create a persistent Cradl agent run and document, then upload one document for asynchronous extraction in a single call. This consumes processed-page quota. It returns immediately after upload and does not poll extraction; use the composite
- **Start Agent Run** — Create a processing run for an existing Cradl AI agent. This creates persistent run state; attaching and processing document content against the run consumes the workspace's monthly processed-page quota.
- **Upload Document to Run** — Create a document attached to a Cradl AI agent run and upload its PDF, image, or email bytes. The upload starts asynchronous processing and consumes the workspace's monthly processed-page quota.

## Setup

1. Create or open a Switchy Project.
2. Open Integrations and connect Cradl AI.
3. Authorise through oauth2.
4. Teammates can now @-mention Cradl AI tools in chat.

---
Last verified: 2026-09-04T02:00:56.012Z  
Canonical URL: https://switchy.build/directory/mcps/cradl-ai