# Invofox — how to use (mcp.ai)

Connect your Invofox account and use 10 tools for document data extraction straight from your AI agent. Connect with your own API key. Invofox extracts structured data and OCR text from invoices and other business documents and supports document-processing workflows.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_invofox?ms=1787295900000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `invofox_create_company`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/invofox`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/invofox/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/invofox/create/company` — Create a managed company collection used to organize document processing.
  - body: { name: string, tax_id: string, client_data?: object, country_code: string }
- `POST https://api.mcp.ai/api/invofox/delete/company` — Permanently delete one managed company by ID. This destructive operation cannot be undone.
  - body: { company_id: string }
- `POST https://api.mcp.ai/api/invofox/get/document` — Get one processed document with extracted fields, confidence, processing metadata, and signed source or image URLs.
  - body: { document_id: string }
- `POST https://api.mcp.ai/api/invofox/get/document/text` — Return plain OCR text for each page of a processed document.
  - body: { document_id: string }
- `POST https://api.mcp.ai/api/invofox/get/import` — Get an asynchronous import's status, document count, and file processing records after documents were queued.
  - body: { import_id: string }
- `POST https://api.mcp.ai/api/invofox/list/companies` — Find managed companies by country, tax ID, or name using bounded offset pagination.
  - body: { name?: string, limit?: integer, tax_id?: string, next_cursor?: string, country_code?: string }
- `POST https://api.mcp.ai/api/invofox/list/documents` — Find processed documents using extraction-field filters, sorting, field selection, and bounded offset pagination.
  - body: { sort?: string, limit?: integer, filter?: object, select?: string[], next_cursor?: string }
- `POST https://api.mcp.ai/api/invofox/process/documents/by/url` — Queue one or more documents from public HTTPS URLs for asynchronous extraction. Returns the import and file IDs needed to track processing.
  - body: { info?: object, files: object[] }
- `POST https://api.mcp.ai/api/invofox/set/document/state` — Move a document to pending correction, approved, discarded, or exported. Approval, discard, and export may trigger irreversible downstream workflows.
  - body: { document_id: string, public_state: string }
- `POST https://api.mcp.ai/api/invofox/update/document` — Correct extracted document fields, update client metadata, or do both for an existing processed document.
  - body: { data?: object, client_data?: object, document_id: string }

## Example prompts
- "What can I do in Invofox?"
- "Show me a summary of my Invofox account"

## More
- Page: https://mcp.ai/invofox
- Agent spec (llms.txt): https://mcp.ai/invofox/llms.txt
- Postman collection: https://mcp.ai/invofox/postman.json