# Airparser — MCP server on mcp.ai
> Connect your Airparser account and use 10 tools for document data extraction straight from your AI agent. Connect with your own API key. Airparser extracts structured data from emails, documents, and other files using AI-powered parsing.

By: mcp.ai · official
Page: https://mcp.ai/airparser

## Connect (MCP protocol)
Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_airparser?ms=1787293740000
Add it as a custom/remote MCP connector, then authenticate when prompted.

## REST API (no MCP client required)
Every tool is also a REST endpoint, authed with a workspace API key.
Discover: GET https://api.mcp.ai/api/airparser/_endpoints   # public; lists every endpoint
Call:     POST https://api.mcp.ai/api/airparser/<endpoint>
  Authorization: Bearer sk_live_…   # create one at https://mcp.ai/settings/api-keys
  Content-Type: application/json
  Body: { …args }   →   { "ok": true, "tool": "<id>", "result": { … } }

## Developer docs
How to use (MCP or REST), markdown: https://mcp.ai/airparser/skill.md
Postman collection (v2.1): https://mcp.ai/airparser/postman.json

## Tools
- airparser_clone_extraction_schema(source_inbox_id: string, destination_inbox_id: string) — Replace a destination inbox's extraction schema with a copy of a source inbox's schema.
- airparser_create_inbox(name: string, llm_engine?: string) — Create an Airparser inbox/parser for a document family using a text or vision extraction engine.
- airparser_delete_inbox(inbox_id: string, confirm_permanent_deletion: boolean) — Permanently delete an Airparser inbox and every document it contains. This destructive, cascading operation cannot be undone and requires explicit confirmation.
- airparser_get_account_usage() — Return the connected Airparser account's role, verification state, plan, and parsing-credit usage without exposing personal, secret, or internal account fields.
- airparser_get_document(source?: string, document_id: string, detail_level?: string) — Get parsed output and status for a document, optionally including extended source and navigation details.
- airparser_get_inbox(inbox_id: string) — Get one Airparser inbox, including its current extraction schema and useful parsing configuration.
- airparser_list_documents(query?: string, to_date?: string, inbox_id: string, per_page?: integer, from_date?: string, next_cursor?: string) — List and search documents in one inbox, one page at a time.
- airparser_list_inboxes() — List the Airparser inboxes available to the connected account.
- airparser_parse_document_sync(file: object, inbox_id: string, metadata?: object) — Upload one document to an inbox and wait for its extracted JSON. This non-idempotent operation consumes plan credits, including one credit per PDF page. Do not retry automatically after an ambiguous f
- airparser_upsert_extraction_schema(fields: object[], inbox_id: string) — Create or completely replace the extraction schema used by an Airparser inbox. The fields array is the complete replacement, not a partial update.

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

## Links
Docs: https://mcp.ai/docs/mcps/airparser
Website: https://mcp.ai/mcps/airparser