pingen-mcp
Enables sending physical letters (including registered mail) from PDFs via the Pingen API, with tools to manage drafts, submit, track, and cancel letters.
README
pingen-mcp
MCP server for Pingen v2 — send physical letters (A-Post / B-Post / registered / Einschreiben) from a PDF and track their status, straight from any MCP client. Uses the official Pingen REST API (no browser automation), data hosted in Switzerland.
Auth
OAuth2 client_credentials. Create an OAuth client in the Pingen dashboard
(Settings → API), then provide the credentials via env vars or, on macOS,
the login keychain:
security add-generic-password -a pingen -s pingen-mcp-client-id -w "<CLIENT_ID>" -U
security add-generic-password -a pingen -s pingen-mcp-client-secret -w "<CLIENT_SECRET>" -U
# optional (auto-detected from /organisations otherwise):
security add-generic-password -a pingen -s pingen-mcp-org-uuid -w "<ORG_UUID>" -U
Env-var alternative: PINGEN_CLIENT_ID, PINGEN_CLIENT_SECRET,
PINGEN_ORG_UUID, PINGEN_API_BASE (default https://api.pingen.com).
Never commit credentials.
Tools
| Tool | Purpose |
|---|---|
pingen_status |
verify credentials, show the active organisation |
pingen_list_letters |
list letters with status + tracking |
pingen_send_letter |
upload a PDF and create a letter — DRAFT by default (auto_send=false) |
pingen_submit_letter |
send an existing draft with a delivery product (physically mails it) |
pingen_get_letter |
status/tracking of one letter |
pingen_cancel_letter |
cancel a submitted letter (where cancellable) |
pingen_delete_letter |
delete a draft / not-yet-sent letter |
pingen_letter_events |
tracking history (created → submitted → sent → delivered …) |
pingen_download_letter |
download the letter PDF (once processed/sent) |
Safety
pingen_send_letter creates a draft unless you pass auto_send: true.
Nothing is physically mailed until you call pingen_submit_letter (or send
with auto_send: true). Review the draft in the Pingen dashboard first.
Delivery products (Switzerland)
Pass delivery_product as e.g. cheap (B-Post), fast (A-Post),
registered (Einschreiben), premium. Exact availability depends on your
organisation/plan — check the Pingen dashboard.
Install
git clone git@github.com:sapn95/pingen-mcp.git
cd pingen-mcp && npm install
claude mcp add --scope user pingen -- node /path/to/pingen-mcp/index.js
Example
pingen_send_letter { "file_path": "/…/Einsprache_2024.pdf", "delivery_product": "registered", "address_position": "left" }
→ creates a draft; review in dashboard, then
pingen_submit_letter { "letter_id": "…", "delivery_product": "registered" }
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.