Skip to content
Scalekit Docs
Talk to an Engineer Dashboard

Connect AI agents to the Holded MCP server

Vendor MCP
Open markdown

The Holded MCP connector routes your AI agent's tool calls to Holded's own MCP server through Scalekit. Each user signs in to Holded once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 142 tools.

Tools
142
What they doRead · write · destructive
142 · 0 · 0142 read0 write0 destructive
Users sign in with
OAuth app
Your own Holded MCP server app

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 Holded MCP connection

    In AgentKit > Connections, create a Holded MCP connection and copy its redirect URI. The name you give it is the connection_name your code passes. See Configure connections.

  4. Register an OAuth app

    Holded MCP server connections use your own OAuth app. Register one with Holded MCP server and add the redirect URI you copied.

    Then enter the app's Client ID and Client Secret on the Holded MCP connection.

  5. 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 = 'holdedmcp'
    const identifier = 'user_123'
    // Generate an authorization link for the user
    const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
    console.log('Authorize Holded MCP:', 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: 'holdedmcp_get_usage',
    toolInput: {},
    })
    console.log(result)
    Terminal window
    npx tsx quickstart.mts

    Each user signs in once. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool
Try in PlaygroundRequest a tool
  • holdedmcp_download_inbox_file**Required permission:** `inbox:inbox.read` Returns the raw content of a file attached to an incoming document.Read-only

    Download a file from an inbox document

    **Required permission:** `inbox:inbox.read` Returns the raw content of a file attached to an incoming document. Use `?variant=inline` to display the file in-browser with 24-hour caching instead of triggering a download.

    Inputs

    filenamestringrequired
    Name of the file to retrieve
    incomingDocumentIdstringrequired
    Incoming document identifier
    variantstring
    Delivery mode: download (attachment) or inline (display with cache)one of downloadinlinedefault download
  • holdedmcp_find_invoices_by_document_number**Required permission:** `sales:invoices.read` Returns invoices in your account whose document number matches the given value.Read-only

    Find invoices by document number

    **Required permission:** `sales:invoices.read` Returns invoices in your account whose document number matches the given value. The match is **fuzzy autocomplete**: partial prefixes (e.g. `F260`) return all invoices that start with that token, and minor typos are tolerated. Results are scored by relevance and limited to the authenticated account. Draft, deleted and cancelled invoices are excluded. Results are cursor-paginated: the response includes a `cursor` value and a `has_more` boolean. Pass the `cursor` to the next request to fetch the following page.

    Inputs

    document_numberstringrequired
    Document number to look up. Supports prefixes (e.g. `F260`) and tolerates minor typos.
    cursorstring
    Pagination cursor returned by the previous response. Omit to start from the first page.
    limitinteger
    Maximum number of invoices to return per page.default 50
  • holdedmcp_get_banking_account**Required permission:** `accounting:banks.read` Retrieves the full details of a single banking account by its unique identifier.Read-only

    Get a banking account by ID

    **Required permission:** `accounting:banks.read` Retrieves the full details of a single banking account by its unique identifier. The response includes the current balance, bank details (IBAN, BIC), synchronization status, and archived state.

    Inputs

    idstringrequired
    Banking account identifier
  • holdedmcp_get_booking**Required permission:** `crm:booking-services.read` Returns a single booking identified by its unique ID.Read-only

    Get a booking by ID

    **Required permission:** `crm:booking-services.read` Returns a single booking identified by its unique ID.

    Inputs

    bookingIdstringrequired
    Booking ID (24-char hex ObjectId)
  • holdedmcp_get_booking_location_slots**Required permission:** `crm:booking-services.read` Returns available time slots for a specific service at a location on a given day.Read-only

    Get available slots for a location

    **Required permission:** `crm:booking-services.read` Returns available time slots for a specific service at a location on a given day. The response also includes the booking form fields (under `form`) that must be collected from the user before calling Create a booking.

    Inputs

    daystringrequired
    Date in YYYY-MM-DD format
    locationIdstringrequired
    Location ID (24-char hex ObjectId)
    service_idstringrequired
    Service identifier
  • holdedmcp_get_contact**Required permission:** `contacts:contacts.read` Retrieves the full details of a single contact by its unique identifier.Read-only

    Get a contact by ID

    **Required permission:** `contacts:contacts.read` Retrieves the full details of a single contact by its unique identifier. The response includes all contact data: billing address, shipping addresses, contact persons, custom fields, default invoicing settings, social networks, and accounting records. Use this endpoint when you need the complete contact profile — for list views, prefer the List contacts endpoint which returns the same fields but paginated.

    Inputs

    contactIdstringrequired
    Contact ID (24-char hex ObjectId)
  • holdedmcp_get_contact_attachment**Required permission:** `contacts:contacts.read` Downloads a single attachment from a contact.Read-only

    Get a contact attachment

    **Required permission:** `contacts:contacts.read` Downloads a single attachment from a contact. The response body contains the raw file bytes. Use the `Content-Disposition` header to obtain the original file name.

    Inputs

    contactIdstringrequired
    Contact ID (24-char hex ObjectId)
    filenamestringrequired
    Attachment file name (case-insensitive match)
  • holdedmcp_get_contact_group**Required permission:** `contacts:contacts.read` Returns a single contact group by its ID.Read-only

    Get a contact group

    **Required permission:** `contacts:contacts.read` Returns a single contact group by its ID.

    Inputs

    contactGroupIdstringrequired
    Contact Group ID (24-char hex ObjectId)