Skip to main content
Glama
norman-finance

Norman Finance MCP Server

Official

send_invoice

Send invoices via email with customizable subject, body, and recipient options. Supports additional email addresses, company copy, and custom client email fields for streamlined invoice distribution.

Instructions

Send an invoice via email.

Args:
    invoice_id: ID of the invoice to send
    subject: Email subject line
    body: Email body content
    additional_emails: List of additional email addresses to send to
    is_send_to_company: Whether to send the copy to the company email (Owner)
    custom_client_email: Custom email address for the client (By default the email address of the client is used if it is set)
    
Returns:
    Response from the send invoice request

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
additional_emailsNo
bodyYes
custom_client_emailNo
invoice_idYes
is_send_to_companyNo
subjectYes

Implementation Reference

  • The core handler function for the 'send_invoice' MCP tool. It constructs and sends a POST request to the backend API to email the invoice with customizable subject, body, recipients, and options.
    @mcp.tool()
    async def send_invoice(
        ctx: Context,
        invoice_id: str,
        subject: str,
        body: str,
        additional_emails: Optional[List[str]] = None,
        is_send_to_company: bool = False,
        custom_client_email: Optional[str] = None
    ) -> Dict[str, Any]:
        """
        Send an invoice via email.
        
        Args:
            invoice_id: ID of the invoice to send
            subject: Email subject line
            body: Email body content
            additional_emails: List of additional email addresses to send to
            is_send_to_company: Whether to send the copy to the company email (Owner)
            custom_client_email: Custom email address for the client (By default the email address of the client is used if it is set)
            
        Returns:
            Response from the send invoice request
        """
        api = ctx.request_context.lifespan_context["api"]
        company_id = api.company_id
        
        if not company_id:
            return {"error": "No company available. Please authenticate first."}
        
        send_url = urljoin(
            config.api_base_url,
            f"api/v1/companies/{company_id}/invoices/{invoice_id}/send/"
        )
        
        send_data = {
            "subject": subject,
            "body": body,
            "isSendToCompany": is_send_to_company
        }
        
        if additional_emails:
            send_data["additionalEmails"] = additional_emails if additional_emails else []
        if custom_client_email:
            send_data["customClientEmail"] = custom_client_email
            
        return api._make_request("POST", send_url, json_data=send_data)
  • Registration block in the main server creation function, where register_invoice_tools(server) is called to register the send_invoice tool (imported from norman_mcp.tools.invoices).
    register_client_tools(server)
    register_invoice_tools(server)
    register_tax_tools(server)
    register_transaction_tools(server)
    register_document_tools(server)
    register_company_tools(server)
    register_prompts(server)
    register_resources(server)
  • A @mcp.prompt() helper that provides a conversational template to guide users through the process of invoking the send_invoice tool, prompting for subject, body, and recipient options.
    def send_invoice_prompt(invoice_id: str) -> List[base.Message]:
        """
        Create a prompt for sending an invoice via email.
        
        Args:
            invoice_id: ID of the invoice to send
            
        Returns:
            A list of messages forming a conversation about sending an invoice
        """
        return [
            base.UserMessage(f"I want to send invoice {invoice_id} to the client."),
            base.AssistantMessage("I'll help you send this invoice. What should the email subject line be?"),
            base.UserMessage("Invoice for your recent order"),
            base.AssistantMessage("Great! And what message would you like to include in the email body?"),
            base.UserMessage("Dear Client,\n\nPlease find attached the invoice for your recent order. Payment is due within 14 days.\n\nThank you for your business!\n\nBest regards,"),
            base.AssistantMessage("Would you like to send a copy to yourself or any additional recipients?"),
            base.UserMessage("Yes, please send a copy to myself."),
            base.AssistantMessage("I'll prepare the email with the invoice attachment and send it to the client with a copy to you. Would you like to review the email before sending?")
        ]
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It states the action ('send an invoice via email') but lacks critical details: it doesn't mention authentication requirements, rate limits, whether the invoice status changes after sending, error handling, or what 'Response from the send invoice request' entails. This is inadequate for a mutation tool with zero annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a brief purpose statement followed by parameter explanations and a returns section. It's front-loaded and efficient, though the 'Returns' line is vague and could be more informative, slightly reducing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (6 parameters, mutation action) and lack of annotations/output schema, the description is partially complete. It excels in parameter semantics but falls short in behavioral transparency and usage guidelines, leaving gaps in understanding how and when to use the tool effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds significant value beyond the input schema, which has 0% schema description coverage. It provides clear explanations for all 6 parameters, including optional behaviors (e.g., 'By default the email address of the client is used if it is set'), default logic, and purpose. This fully compensates for the schema's lack of descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose as 'Send an invoice via email,' which is a specific verb+resource combination. It distinguishes itself from sibling tools like 'send_invoice_overdue_reminder' by focusing on general invoice sending rather than reminders, though it doesn't explicitly contrast with other email-related tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., invoice must exist), compare with other tools like 'send_invoice_overdue_reminder,' or specify scenarios where it's appropriate, leaving usage context unclear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Related Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/norman-finance/norman-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server