Outvoicer MCP
Enables AI assistants to prepare and create invoices via Outvoicer's invoicing platform using Streamable HTTP MCP.
README
Outvoicer MCP
An unofficial MCP server for preparing and creating invoice drafts in Outvoicer.
Purpose
I already use MCP servers, so connecting Outvoicer was a natural next step. Its public API makes it possible to prepare, create, and send invoices through conversation.
This project was created in collaboration with Martin Sookael, founder of Outvoicer.
I use OpenCode, but the server also works with compatible clients such as ChatGPT and Claude.
Scope
The current focus is limited to:
- Creating invoices
- Previewing invoices
- Sending invoices
Currently, it does not manage Outvoicer account data, integrations, or settings. These can be managed at outvoicer.com.
Authentication
Public lebo.agency endpoints use OAuth through oauth.lebo.agency.
The server validates signed OAuth access tokens, then resolves the user's selected Outvoicer connection server-side.
- Protected resource discovery uses RFC 9728 metadata.
- Authorization uses the OAuth authorization code flow with PKCE
S256and dynamic client registration. - OAuth resource indicators bind authorization, access tokens, and JWT audiences to the Outvoicer MCP URL.
- JWT access tokens are verified against the authorization server's JWKS with exact issuer, audience, expiry, and scope checks.
- Tools advertise and enforce
invoice:readandinvoice:createindependently.
Security
- Public access is protected by OAuth.
- OAuth access is limited to the Outvoicer MCP resource and the user's stored connection.
- Requests are stateless and access tokens are validated on every request.
- OAuth access tokens are never forwarded to Outvoicer.
- Responses and telemetry exclude sensitive data.
Technology
- TypeScript
- Bun runs the application and manages packages.
- Cloudflare Workers hosts the server.
- Hono handles HTTP requests, and the Model Context Protocol SDK provides MCP support.
- Zod validates data.
- Langfuse and OpenTelemetry provide tracing and observability.
About
This project is maintained by Kristjan Suursoho, who works with Outvoicer as a freelancer. It is an unofficial project and is not maintained or published by Outvoicer.
The Outvoicer API, internally known as Tetris, is available at api.outvoicer.com. OpenAPI documentation is available there.
License
Licensed under the MIT License.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.