FrankKi

by datPascal

Not rated
GitHub

About

Agents send real printed letters worldwide with quotes, previews, approval controls, and tracking through a hosted remote MCP server.

Details

Author
datPascal
Categories
Communication, Other, Automation, API

Setup

Install FrankKi in your MCP client (Claude Desktop, Cursor, Windsurf, and others).

Repository: https://github.com/datpascal/frankki-mcp

Follow the installation instructions in the repository README, then restart your MCP client.

Hosted, remote MCP server. Nothing to install, nothing to self-host.Point your agent athttps://mcp.frankki.app(remote, streamable-http, OAuth 2.1 or API key). This repository is the public manifest, documentation and changelog for that server; the server itself is closed-source and runs on our own infrastructure, which is why there is nosrc/directory here.

Physical mail for AI agents.With one tool call, FrankKi MCP lets an agent send a real, printed letter to a physical address anywhere in the world. Compose, price, send, and track. The document is printed, franked, and delivered by postal partners worldwide.

This is the official Model Context Protocol (MCP) server forFrankKi. It is built for B2B and developer use: give your agents, backends, and automated workflows the ability to put real letters in the mail, at scale, worldwide.

Website:frankki.app· MCP for humans and agents:frankki.app/mcp(English:frankki.app/en/mcp)

- What is FrankKi MCP?
-
Why physical mail via MCP?
-
What your agent can do
-
Quick start for humans
-
Quick start for AI agents
-
Authentication
-
Wallet and pricing
-
Safety and human-in-the-loop
-
Sandbox
-
Compliance
-
How a send actually works
-
Discovery and server manifest
-
Documentation
-
FAQ
-
Links

FrankKi MCP is the agent-native interface toFrankKi's physical mail infrastructure. FrankKi composes, prints, and physically mails letters. This server exposes that capability to software: your model drafts a letter and sends it, and a real document arrives at the recipient's address.

Delivery isworldwide, handled by our postal partners in each destination country. It is primarily aB2B and developer product: if you are building an assistant, an ops automation, or a backend that needs to produce and dispatch physical correspondence, this is your physical-output layer.

Some things still have to arrive on paper: formal and legal notices, transactional and compliance mail, contract confirmations, dunning and reminders, customer onboarding, official correspondence. These workflows usually dead-end at "now a human prints this and walks to a postbox." FrankKi MCP removes that step. The same agent that drafts the letter can send it, worldwide, and track delivery.

- Dunning and payment reminders
- Cancellations, terminations, objections, and other formal notices
- Contract and order confirmations
- Customer and account notifications
- Onboarding and welcome letters
- Any workflow whose last step must be a physical letter

The server exposes a focused, scoped tool set. The core send flow:

Beyond the core flow there are tools for attachments, letterheads and signatures, sender profiles, send presets, scheduled sends, order cancellation, posting receipts (Einlieferungsbeleg), client (Mandanten) lookups, and GoBD/DATEV archive exports. The full list with scopes and side effects:docs/tools.md. The authoritative, versioned list is always what the server returns from the MCPtools/listmethod.

Composition is text-first: you provide the letter content and the recipient, and FrankKi produces the correctly laid-out document (DIN 5008 by default). Attachments are supported. Sending a pre-rendered arbitrary PDF is intentionally not part of the platform.

You do not clone or self-host anything. The FrankKi MCP server is hosted. You point your MCP client at it and authenticate.

1. Get access.Create a partner account and issue a key from the dashboard atfrankki.app/mcp. Fund your wallet, or use thesandboxfirst (no real mail).

2a. Claude Desktop and clients with native remote support.Add a custom connector pointing at the endpoint. OAuth runs in your browser on first use:

{ "mcpServers": { "frankki": { "url": "https://mcp.frankki.app" } } }

2b. Clients that only speak stdio(older Claude Desktop, some Cursor setups). Bridge withmcp-remote:

{ "mcpServers": { "frankki": { "command": "npx", "args": ["-y", "mcp-remote", "https://mcp.frankki.app"] } } }

2c. Headless with an API key(no interactive browser). Pass the key as a bearer header:

{ "mcpServers": { "frankki": { "command": "npx", "args": [ "-y", "mcp-remote", "https://mcp.frankki.app", "--header", "Authorization: Bearer ${FRANKKI_API_KEY}" ] } } }
claude mcp add --transport http frankki https://mcp.frankki.app

Restart the client, and your model can now send letters. Ask it something like:"Send this payment reminder to the address on file, but show me the price first."

Step-by-step guides for Cursor, VS Code, Windsurf, Zed, the OpenAI Agents SDK, and LangChain:docs/clients.md.

The server is standardstreamable HTTPMCP. Discovery, endpoint, and auth in one place:

- Endpoint:https://mcp.frankki.app
- Registry name:app.frankki/letters(published in the Official MCP Registry, version 1.0.0)
- Auth metadata:https://mcp.frankki.app/.well-known/oauth-authorization-server(OAuth 2.1, dynamic client registration) or a static bearer API key
- Machine-readable overview:https://frankki.app/llms.txt

import { Client } from "@modelcontextprotocol/sdk/client/index.js"; import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js"; const transport = new StreamableHTTPClientTransport( new URL("https://mcp.frankki.app"), { requestInit: { headers: { Authorization: Bearer ${process.env.FRANKKI_API_KEY} } } } ); const client = new Client({ name: "my-agent", version: "1.0.0" }); await client.connect(transport); const { tools } = await client.listTools(); console.log(tools.map((t) => t.name)); const price = await client.callTool({ name: "shipping_quote", arguments: { recipientCountry: "US", deliveryType: "standard" }, });
from mcp import ClientSession from mcp.client.streamable_http import streamablehttp_client url = "https://mcp.frankki.app" headers = {"Authorization": f"Bearer {FRANKKI_API_KEY}"} async with streamablehttp_client(url, headers=headers) as (read, write, _): async with ClientSession(read, write) as session: await session.initialize() tools = await session.list_tools() print([t.name for t in tools.tools])

- OAuth 2.1for interactive clients (Claude Desktop, IDEs). The consent screen shows what the agent is allowed to do, and read-only scopes are granted by default. Best when an end user connects their own FrankKi account.
- API key(bearer token) for headless agents, servers, and CI. Issue and rotate keys in the dashboard. Each key can carry a spending limit and an allowed-tools scope, so a key that may look up prices does not have to be a key that may spend money.

FrankKi runs on aprepaid wallet. You top it up (via Stripe), and each send draws from the balance. No surprise post-paid invoices, and an out-of-credit agent simply cannot spend.

- Pricing depends on thedestination country. A domestic letter within Germany starts at3,49 EUR; international sends are priced per destination.
- Registered mail and other service levels are available where the destination supports them.
- Volume tiers (Staffelpreise) reduce the per-letter price at scale.

Always callshipping_quotefor the live, exact figure beforeorder_send. Prices are authoritative from the server, never hardcode them.

Sending physical mail is irreversible and costs money, so the platform is cautious by default:

- Honest annotations.order_sendandorder_send_batchare annotated as destructive; read tools as read-only. Your agent can gate on this, andorder_sendaccepts amaxCostEuroscap that aborts the send if the live price exceeds it.
- Approval queue.Route sensitive letters throughapproval_submitfor afour-eyeshuman check before anything is printed. Every decision is logged.
- Per-key spending limits and tool scopes.Cap what an automated key can spend, and restrict which tools it may call.
- Preview before commit.letter_create_draftreturns a rendered preview andshipping_quotereturns the cost, so an agent or a human can confirm beforeorder_send.

Test the full flow without mailing anything. Request asandbox keyfrom the dashboard, point at the same endpoint, and you get a funded test wallet. Composition, pricing, and status all behave like production, but no paper is printed and no charge is made. Build and demo your integration end to end, then swap in a live key.

Enterprise and EU-grade, for teams that need it:

- GoBD-compliantarchiving of every send, with retrievable receipts.
- DATEVand genericDMSexports for accounting and document management.
- DSGVO / GDPR: letter data is processed in the EU.
- Platform and messages available inEnglish and German.
- Your agent callsletter_create_draftwith the text and a recipient. FrankKi renders a professionally formatted document.
- shipping_quotereturns the exact cost for that destination. The agent, or a human via the approval queue, confirms.
- order_sendcharges the prepaid wallet atomically and hands the job to fulfillment.
- FrankKi prints the letter and hands it off for delivery worldwide via our postal partners.
- Status flows back throughorder_status: printed, posted, and, where supported, delivered.order_einlieferungsbelegreturns the posting receipt.

For directories and registries, this repo publishesserver.json(Official MCP Registry schema, nameapp.frankki/letters) and a repo-levelllms.txtfor AI-assisted discovery.

Found this server through an MCP directory? The canonical source of truth is alwaysfrankki.app/mcp.

Is the letter really printed and mailed, or is it email?Real paper. It is printed, franked, and delivered by postal partners. This is not email.

Which countries can it deliver to?Worldwide. Useshipping_quoteto confirm reach and cost for a specific destination.

Do I host the server?No. FrankKi hosts it. This repo is documentation,server.json, and examples. You connect a client or agent to the hosted endpoint.

Is this for consumers or businesses?Primarily B2B and developer use: agents, backends, and automated workflows that need to dispatch physical mail at scale.

What if my agent goes rogue?It cannot spend beyond the wallet balance or a key's spending limit, sensitive letters can be forced through a human approval queue, and destructive tools are clearly annotated. Start in thesandbox.

Is there an API without MCP?Yes, FrankKi also exposes a REST API. The MCP server is the agent-native front door. Seefrankki.app/mcp.

- Homepage:https://frankki.app
- MCP for humans and agents:
https://frankki.app/mcp·https://frankki.app/en/mcp
- Machine-readable overview:
https://frankki.app/llms.txt
- Endpoint:
https://mcp.frankki.app
- Registry name:app.frankki/letters(published in the Official MCP Registry, version 1.0.0)

Built by the team behindFrankKi: physical mail infrastructure for software, so your agents and workflows can send real letters worldwide without ever touching a printer.

Interact with any other SaaS applications on behalf of your customers.

Connects AI agents to the Feishu/Lark platform via its OpenAPI to automate tasks like document processing, conversation management, and calendar scheduling.

An open-source messaging server for client-to-client communication using MCP HTTP Streamable messaging.

An open-source messaging server for client-to-client communication using MCP HTTP streaming, configurable via an external JSON file.

Integrates Typebot's REST API as callable tools, allowing interaction with Typebot forms and chats.

Manage oVice workspaces, groups, users, and send notifications through the oVice API.

Send a one-off fax from inside ChatGPT or Claude. Pay-per-use, $2-$4.50 per fax, charged only after delivery. No PromptFax account, no subscription, no API key to manage.

MCP server for electronic consignment notes (eCMR). Create, sign, manage, and track electronic transport documents with QR codes, PDF generation, and digital signatures through the Cargoffer ECMR API. Designed for AI agents like Claude Desktop, Cursor, and Cline

Connects AI agents to the Feishu/Lark platform for automating tasks like document processing, conversation management, and calendar scheduling.

Connects AI agents to the Feishu/Lark platform to automate document processing, conversation management, and calendar scheduling via its OpenAPI.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.