Integration

Parseur integration

Parseur extracts structured data from emails, PDFs and other documents sent to a mailbox (Parseur's API calls a mailbox a parser). Upload a file or an email-like text document into a mailbox, list a mailbox's documents and read each one with its parsed result, reprocess, skip, copy or delete documents and read their processing logs, create, update, copy and delete mailboxes and read the JSON schema of their extracted fields, manage custom downloads (CSV or Excel exports of chosen fields), list, read, copy and delete templates, and create webhooks and enable or disable them per mailbox. Processing is asynchronous: an upload confirms receipt, and the parsed result appears on the document once processing finishes. Templates cannot be created or edited through the API; deleting a webhook (whose response is not JSON) and the app's bootstrap configuration route are not exposed. Requests are limited to 5 per second per IP with an initial burst of 20. Authentication is an API key created in the Parseur app under Account, API keys, sent in the Authorization header.

Connect Parseur How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Parseur.Built from the 27 Parseur tools below, on the connection you add once.

What you can do with Parseur

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Document, 8 operations

copy_documentCopy documentPOSTCopies a document into another mailbox. The copy runs in the background and shows up in the target mailbox after a few seconds; the answer carries an information notice.
delete_documentDelete documentDELETEDeletes a document from its mailbox.
get_documentGet documentGETReturns one document with its status, metadata, download URLs, text content and parsed result. The result field is a JSON-encoded string: decode it to read the extracted fields. Poll this tool to learn when processing has finished.
list_mailbox_documentsList mailbox documentsGETLists a mailbox's documents, 25 per page by default: status, received and processed times, credits used, download URLs. Filter by status, received date range or search term, sort with ordering, and set with_result to include each parsed result.
reprocess_documentReprocess documentPOSTReprocesses a document: parses it again and resends all of its exports. Runs in the background; the answer carries an information notice.
skip_documentSkip documentPOSTMarks a document as skipped so it is not processed, and returns the updated document.
upload_document_fileUpload document filePOSTUploads a file (PDF, image, EML, office document and the other formats Parseur supports) into a mailbox as a new document. Processing is asynchronous: the answer lists each received attachment with its DocumentID, and the parsed data appears later.
upload_email_documentUpload email documentPOSTSends an email or text document to a mailbox: the mailbox address must appear in recipient, to, cc or bcc. body_html takes precedence over body_plain when both are present. Processing is asynchronous: a successful answer confirms receipt only.

Mailbox, 6 operations

copy_mailboxCopy mailboxPOSTCopies a mailbox (parser) with its settings. The copy runs in the background and shows up in list_mailboxes after a few minutes; the answer carries an information notice.
create_mailboxCreate mailboxPOSTCreates a mailbox (parser). Every field is optional: set a name, an email prefix, the AI engine and AI instructions, the extracted fields in parser_object_set, page and split settings, and which metadata fields to add to each result.
delete_mailboxDelete mailboxDELETEDeletes a mailbox (parser). Deletion runs in the background and can take a while; the answer carries an information notice.
get_mailboxGet mailboxGETReturns one mailbox (parser) with its settings, document counts, enabled metadata fields, its extracted fields, and its active (webhook_set) and available (available_webhook_set) webhooks.
list_mailboxesList mailboxesGETLists the mailboxes (parsers) of the account, 25 per page by default, with each one's id, name, email prefix, document counts per status, template and webhook counts and enabled metadata fields.
update_mailboxUpdate mailboxPUTUpdates a mailbox (parser): its name, email prefix, AI engine and instructions, extracted fields (parser_object_set), page and split settings, retention or metadata fields. Send only the fields to change.

Custom download, 4 operations

create_custom_downloadCreate custom downloadPOSTCreates a custom download on a mailbox: a saved CSV and Excel export of the fields listed in items, either of the mailbox's top-level fields (type PARSER) or of the columns of one table field (type PARSER_FIELD with parser_field_id).
delete_custom_downloadDelete custom downloadDELETEDeletes a custom download from a mailbox.
list_custom_downloadsList custom downloadsGETLists the custom downloads of a mailbox: saved CSV and Excel exports of chosen fields, each with its id, name, type, field items and its csv_download and xls_download paths.
update_custom_downloadUpdate custom downloadPATCHUpdates a custom download of a mailbox: its name, type, table field and the list of exported fields.

Template, 4 operations

copy_templateCopy templatePOSTCopies a template into another mailbox. The answer carries an information notice.
delete_templateDelete templateDELETEDeletes a template.
get_templateGet templateGETReturns one template with its engine, action, status, margins, field definitions and, for OCR templates, its samples.
list_mailbox_templatesList mailbox templatesGETLists the templates of a mailbox, 25 per page by default, with each template's id, name, engine, action, status, document count and last activity.

Mailbox webhook, 2 operations

disable_mailbox_webhookDisable mailbox webhookDELETEDisables (pauses) a webhook on one mailbox, leaving it active on other mailboxes, and returns the mailbox with its updated webhook_set.
enable_mailbox_webhookEnable mailbox webhookPOSTEnables (activates) a webhook on one mailbox and returns the mailbox with its updated webhook_set.

Document log, 1 operation

list_document_logsList document logsGETLists the processing and export log entries of a document (parsing, webhook and other export attempts), 25 per page by default, each with its status, source, code, message and payload.

Mailbox schema, 1 operation

get_mailbox_schemaGet mailbox schemaGETReturns the JSON schema of the data this mailbox extracts: one property per field and enabled metadata field, with its type and, for objects and tables, its sub-properties.

Webhook, 1 operation

create_webhookCreate webhookPOSTCreates a webhook: a URL Parseur calls with a POST when an event happens. Webhooks belong to the account: after creating one, enable it on each mailbox with enable_mailbox_webhook.

Use Parseur from Claude Code, Cursor or Codex

Connect Parseur in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Parseur operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Parseur

Create your workspace
Sign up free. Nothing to install.
Connect Parseur once
Add your Parseur connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.