Skip to content
Scalekit Docs
Talk to an Engineer Dashboard

Connect AI agents to Parseur

Scalekit connector
Open markdown

The Parseur connector lets your AI agent act in each user's Parseur account. Each user connects their own Parseur API key once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 27 tools.

Tools
27
What they doRead · write · destructive
9 · 12 · 69 read12 write6 destructive
Users sign in with

Setup

  1. Install the SDK

    Terminal window
    npm install @scalekit-sdk/node dotenv
  2. Set your credentials

    Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

    .env
    SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
    SCALEKIT_CLIENT_ID=<your-client-id>
    SCALEKIT_CLIENT_SECRET=<your-client-secret>
  3. Create the Parseur connection

    In AgentKit > Connections, create a Parseur connection. The name you give it is the connection_name your code passes. See Configure connections.

  4. Authorize a user and make your first call

    quickstart.mts
    import { ScalekitClient } from '@scalekit-sdk/node'
    import 'dotenv/config'
    import { createInterface } from 'node:readline/promises'
    const scalekit = new ScalekitClient(
    process.env.SCALEKIT_ENVIRONMENT_URL,
    process.env.SCALEKIT_CLIENT_ID,
    process.env.SCALEKIT_CLIENT_SECRET,
    )
    const actions = scalekit.actions
    const connector = 'parseur'
    const identifier = 'user_123'
    // Generate an authorization link for the user
    const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
    console.log('Authorize Parseur:', link)
    const rl = createInterface({ input: process.stdin, output: process.stdout })
    await rl.question('Press Enter after authorizing...')
    rl.close()
    // Make your first call
    const result = await actions.executeTool({
    connector,
    identifier,
    toolName: 'parseur_mailboxes_list',
    toolInput: {},
    })
    console.log(result)
    Terminal window
    npx tsx quickstart.mts

    Each user opens the link once and enters their Parseur credentials there. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool
Try in PlaygroundRequest a tool
  • parseur_document_getGet one Parseur document with its parsed result.Read-only

    Get Document

    Get one Parseur document with its parsed result. Returns the document's name, status, dates, template, content links and the parsed result JSON. Use parseur_documents_list to find the ID.

    Inputs

    idstringrequired
    ID of the document. Find it with parseur_documents_list. Example: 9a1b2c3d4e5f.
  • parseur_document_logs_listList the processing log entries of a Parseur document (received, parsed, exported, errors).Read-only

    List Document Logs

    List the processing log entries of a Parseur document (received, parsed, exported, errors). Returns results[] of log entries with date, status and message. Use to find why a document failed or was not exported.

    Inputs

    idstringrequired
    ID of the document. Find it with parseur_documents_list. Example: 9a1b2c3d4e5f.
    orderingstring
    Field name to order by (use -prefix for descending) Example: -created.
    pageinteger
    Page number for pagination (default is 1)
    page_sizeinteger
    Number of results per page (default is 25) Example: 50.
    searchstring
    Case-insensitive partial match search Example: invoice.
  • parseur_documents_listList the documents in a Parseur mailbox, with search, status, received-date filters, ordering and paging; optionally include parsed results.Read-only

    List Documents

    List the documents in a Parseur mailbox, with search, status, received-date filters, ordering and paging; optionally include parsed results. Returns results[] of documents with id, name, status, received and processed dates (and result when with_result is true), plus count and next link. Use parseur_document_get for one document.

    Inputs

    idintegerrequired
    ID of the Parseur mailbox. Find it with parseur_mailboxes_list. Example: 12345.
    orderingstring
    Field name to order by (use -prefix for descending) Example: -created.one of name-namecreated-createdprocessed-processedstatus-status
    pageinteger
    Page number for pagination (default is 1)
    page_sizeinteger
    Number of results per page (default is 25) Example: 50.
    received_afterstring
    Filter documents received after this date (yyyy-mm-dd) Example: 2026-11-01.
    received_beforestring
    Filter documents received before this date (yyyy-mm-dd) Example: 2026-11-16.
    searchstring
    Case-insensitive partial match search Example: invoice.
    statusstring
    Filter documents by status Example: INCOMING.one of INCOMINGANALYZINGPROGRESSPARSEDOKPARSEDKOQUOTAEXCSKIPPEDSPLITEXPORTKOTRANSKOINVALID
    tzstring
    Timezone for date filters (e.g. Asia%2FSingapore). Defaults to UTC. Example: Europe/Paris.
    with_resultboolean
    Include parsed result string with each document Example: true.
  • parseur_downloads_listList the custom CSV/Excel downloads (export configurations) of a Parseur mailbox.Read-only

    List Custom Downloads

    List the custom CSV/Excel downloads (export configurations) of a Parseur mailbox. Returns the downloads with id, name, type, selected fields and csv_download/xls_download URLs. Use parseur_download_create to add one.

    Inputs

    idintegerrequired
    ID of the Parseur mailbox. Find it with parseur_mailboxes_list. Example: 12345.
  • parseur_mailbox_getGet one Parseur mailbox with its full settings and fields.Read-only

    Get Mailbox

    Get one Parseur mailbox with its full settings and fields. Returns the mailbox: name, email_prefix, AI engine, fields (parser_object_set), processing options, webhooks and download URLs. Use parseur_mailboxes_list to find the ID.

    Inputs

    idintegerrequired
    ID of the Parseur mailbox. Find it with parseur_mailboxes_list. Example: 12345.
  • parseur_mailbox_schema_getGet the field structure (schema) of a Parseur mailbox's parsed data.Read-only

    Get Mailbox Schema

    Get the field structure (schema) of a Parseur mailbox's parsed data. Returns the JSON schema of the fields and tables Parseur extracts. Use to map parsed results to your own system.

    Inputs

    idintegerrequired
    ID of the Parseur mailbox. Find it with parseur_mailboxes_list. Example: 12345.
  • parseur_mailboxes_listList the Parseur mailboxes (parsers) in the account, with search, ordering and paging.Read-only

    List Mailboxes

    List the Parseur mailboxes (parsers) in the account, with search, ordering and paging. Returns results[] of mailboxes with id, name, email_prefix, document and template counts, plus count and next/previous links. Use parseur_mailbox_get for one mailbox's full settings.

    Inputs

    orderingstring
    Field name to order by (use -prefix for descending) Example: -created.one of name-namedocument_count-document_counttemplate_count-template_countPARSEDOK_count-PARSEDOK_countPARSEDKO_count-PARSEDKO_countQUOTAEXC_count-QUOTAEXC_countEXPORTKO_count-EXPORTKO_countTRANSKO_count-TRANSKO_count
    pageinteger
    Page number for pagination (default is 1)
    page_sizeinteger
    Number of results per page (default is 25) Example: 50.
    searchstring
    Case-insensitive partial match search Example: invoice.
  • parseur_template_getGet one Parseur parsing template.Read-only

    Get Template

    Get one Parseur parsing template. Returns the template with name, status, fields and sample document. Use parseur_templates_list to find the ID.

    Inputs

    idintegerrequired
    ID of the template. Example: 4567.