# Parsio — MCP server on mcp.ai > Connect your Parsio account and use 10 tools for document data extraction straight from your AI agent. Connect with your own API key. Parsio extracts structured data from emails, PDFs, and other documents using configurable parsers. By: mcp.ai · official Page: https://mcp.ai/parsio ## Connect (MCP protocol) Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_parsio?ms=1787293560000 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/parsio/_endpoints # public; lists every endpoint Call: POST https://api.mcp.ai/api/parsio/ Authorization: Bearer sk_live_… # create one at https://mcp.ai/settings/api-keys Content-Type: application/json Body: { …args } → { "ok": true, "tool": "", "result": { … } } ## Developer docs How to use (MCP or REST), markdown: https://mcp.ai/parsio/skill.md Postman collection (v2.1): https://mcp.ai/parsio/postman.json ## Tools - parsio_get_document(document_id: string) — Get one Parsio document and its mailbox-specific parsed JSON fields. - parsio_get_mailbox(mailbox_id: string) — Get settings and parser configuration for one Parsio mailbox. - parsio_list_documents(query?: string, cursor?: string, status?: string[], to_date?: string, per_page?: integer, from_date?: string, mailbox_id: string) — List and filter documents in a Parsio mailbox, one page at a time. - parsio_list_mailboxes() — List the Parsio mailboxes available to the connected account so their IDs can be used for parsing and configuration tasks. - parsio_list_table_fields(mailbox_id: string) — List the extraction fields configured for a Parsio mailbox. - parsio_parse_text_document(html?: string, name?: string, text?: string, metadata?: object, mailbox_id: string, sender_email?: string, recipient_email?: string, wait_for_result?: boolean) — Submit plain text or HTML to an existing template-based or GPT-powered Parsio mailbox, optionally waiting for the parsed result. This operation creates document data and consumes parsing credits. - parsio_reparse_document(document_id: string) — Queue an existing Parsio document to be parsed again. This operation consumes parsing capacity or credits and should not be retried blindly. - parsio_skip_documents(mailbox_id: string, document_ids: string[]) — Mark one or more documents in a Parsio mailbox as skipped. This changes their processing state and cannot be undone through this toolkit. - parsio_update_mailbox(name?: string, mailbox_id: string, email_prefix?: string, alert_email_h?: integer, receive_email?: boolean, collect_emails?: boolean, process_attachments?: boolean) — Update one or more settings on an existing Parsio mailbox. Provide at least one setting; omitted settings remain unchanged. - parsio_upload_document(file: object, metadata?: object, mailbox_id: string, wait_for_result?: boolean) — Upload one file to a Parsio mailbox for parsing, optionally waiting for the parsed result. This operation creates document data and consumes parsing credits. ## Example prompts - "What can I do in Parsio?" - "Show me a summary of my Parsio account" ## Links Docs: https://mcp.ai/docs/mcps/parsio Website: https://mcp.ai/mcps/parsio