A
licenseNot graded
qualityD
maintenanceEnables creation and management of invoices with JSON storage and LaTeX-based PDF rendering. Supports draft creation and professional PDF generation through customizable LaTeX templates.
Apache 2.0
Invompt MCP
by Invompt
This server creates Invompt invoices from raw IML YAML, with optional template selection.
Create invoices: Submit raw Invoice Markup Language (IML) YAML via the
create_invoicetool.Choose a template: Optionally override the invoice template with
professional,minimal, ormodern.Get invoice references: Returns an
invoiceIdand aurlfor the created invoice.No task execution: The tool is forbidden from being used as a sub-task, so it is called directly for invoice creation only.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Invompt MCPCreate a professional invoice for 8 hours of design work at $125 per hour"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Invompt MCP
Turn AI-host work into invoices you review before send. Continue anonymously or OAuth via hosted MCP.
Prefer the hosted connector Registry
com.invompt/invompt->https://mcp.invompt.com/mcpContinue anonymously | review-before-send | www.invompt.com Wellknown: invompt-mcp Local-beta/stdio in this repo is secondary.
Prefer the hosted path above. This repo also ships a pre-1.0 local-beta CLI and Guest stdio bridge for Claude Code or Codex (secondary).
What it does
Turns AI-host context into invoices you review before send.
Lists and updates invoices and clients through the MCP contract.
Hosted path: Continue anonymously or OAuth at mcp.invompt.com.
Secondary local-beta: Guest stdio or hosted OAuth via this package (
invompt-local-beta).
Related MCP server: Invoices Generator MCP Server
Quick start
Hosted (preferred): Continue anonymously at
https://mcp.invompt.com/mcp (or OAuth), then review before send.
Cursor mcp.json (HTTP only - no headers / API key):
{
"mcpServers": {
"invompt": {
"type": "http",
"url": "https://mcp.invompt.com/mcp"
}
}
}Local-beta (secondary): npx --yes invompt-mcp@next setup --host codex --mode oauth
(replace codex/oauth with claude-code/guest). Restart the host, then review before send.
Connection modes
Mode | What it uses | Choose it when |
Hosted | HTTPS MCP endpoint | Default product path (Continue anonymously / OAuth). |
Guest | Local stdio bridge | Local-beta pseudonymous credential (secondary). |
OAuth | Hosted HTTPS via this CLI | Local-beta browser sign-in setup (secondary). |
The bridge does not open a listener or implement invoice business logic. It forwards JSON-RPC only through the selected connection and rejects HTTP redirects.
Security
Guest credentials are stored in the macOS Keychain by default. The optional file fallback requires an explicit flag and uses restricted local permissions. The CLI does not place credentials in a plugin manifest or host configuration, derive a hardware fingerprint, or collect serial and MAC data. Never paste credentials, tokens, or real invoice content into a public issue.
Report a vulnerability through GitHub private vulnerability reporting.
Resources
License
Available Tools
1 toolcreate_invoiceCreate InvoiceB
Create an Invompt invoice from raw IML YAML. Read invompt://spec/iml/v1 first if you need schema guidance.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| iml | Yes | Raw Invoice Markup Language (IML) YAML. | |
| templateId | No | Optional template override. |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| url | Yes | |
| invoiceId | Yes |
TDQS
B3.2/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions creating an invoice but doesn't disclose behavioral traits like permissions needed, whether the operation is idempotent, error handling, or what the output contains. The reference to external documentation adds some context but insufficiently compensates for the lack of built-in transparency.
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 concise with two sentences, front-loading the main action and following with guidance. There's no wasted text, but it could be slightly more structured by explicitly separating purpose from prerequisites.
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 has an output schema, the description doesn't need to explain return values. However, with no annotations and a mutation operation (create), the description lacks completeness in areas like behavioral context and usage prerequisites, making it adequate but with clear gaps for an agent to use effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents both parameters fully. The description adds minimal value beyond the schema by hinting at the need for schema guidance but doesn't provide additional semantics for the parameters. Baseline 3 is appropriate as the schema does the heavy lifting.
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 action ('Create an Invompt invoice') and the input source ('from raw IML YAML'), providing specific verb+resource information. However, it doesn't differentiate from siblings since there are none, and the mention of 'invompt://spec/iml/v1' adds helpful context but doesn't fully clarify the purpose beyond the basic action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by referencing external schema guidance ('Read invompt://spec/iml/v1 first if you need schema guidance'), which suggests when to prepare inputs. However, it lacks explicit when-to-use guidance, alternatives, or exclusions, leaving usage context somewhat vague.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v0.1.0- First observed
create_invoice
TDQS
B3.2/5.0
Scored across 1 tool
Disambiguation5/5
With only one tool, there is no possibility of ambiguity or overlap with other tools, making disambiguation perfect.
Naming Consistency5/5
A single tool inherently has consistent naming, as there are no other tools to compare it against for patterns or deviations.
Tool Count2/5
One tool is too few for a server named 'Invompt MCP', which suggests a broader invoicing domain; this feels thin and likely incomplete for typical invoicing workflows.
Completeness1/5
The server appears focused on invoicing, but with only a create_invoice tool, it lacks essential operations like retrieving, updating, listing, or deleting invoices, making it severely incomplete.
Maintenance
ActivityActive
ResponsivenessNo issues
Related MCP Connectors
Create invoices from your AI assistant and review them before sending. Start without creating an account. Create one later and keep all your invoices. Connect through OAuth at https://mcp.invompt.com/mcp.
Validate, extract, repair and generate French Factur-X / EN16931 invoices via AgentForge API
Create and manage invoices and customers on Jupiter Invoice (MCP, API-key auth).
Validate, generate & convert EU e-invoices (UBL, CII, XRechnung, Factur-X) — EN 16931 pre-validated.
Related MCP Servers
- AlicenseCqualityDmaintenanceProvides access to the Invoices Generator API to create professional, customizable invoices with detailed buyer, seller, and service information. It supports multiple languages, currencies, and tax configurations through a standardized tool interface.1MIT
- AlicenseBqualityDmaintenanceEnables the generation of professional PDF invoices and their distribution via email using customizable templates. It allows users to create, manage, and send invoices with standard business fields like tax rates and line items through natural language.32 npm2MIT
InvoiceXMLofficial
AlicenseNot gradedqualityCmaintenanceInvoiceXML brings e-invoice compliance to your AI agent. Create, validate, convert, render, and extract structured invoices across UBL (Peppol BIS Billing 3.0, used worldwide), CII, Factur-X, ZUGFeRD, and XRechnung, all checked against the EN 16931 standard and official Schematron rules. Ask your assistant to generate a compliant invoice, validate one for errors, or convert between formats, with n5MIT