tollbooth-sample
Allows monetization of weather API calls by accepting Bitcoin Lightning micropayments for tool usage.
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., "@tollbooth-sampleWhat's the current weather in San Francisco?"
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.
tollbooth-sample
Educational Weather Stats MCP Service — the reference implementation for building Tollbooth DPYC monetized API services with Bitcoin Lightning micropayments.
This service wraps the free Open-Meteo weather API
and gates paid tool calls through the Tollbooth
credit system using the @runtime.paid_tool() decorator. Domain tools contain
only business logic; debit, rollback, balance warnings, and constraint evaluation
are handled automatically by the OperatorRuntime. Standard DPYC tools
(balance, purchase, Secure Courier, Oracle, pricing, constraints) are delegated
to the wheel via register_standard_tools().
Build your own operator — the bootstrap-dpyc-operator skill
This repo doubles as a Claude Code plugin. The bootstrap-dpyc-operator skill turns your
existing REST API, stdio MCP, or HTTP MCP into a monetized DPYC Operator MCP: it clones this
template live, wraps your domain logic, and generates a deploy-ready project. You keep writing
business logic — the SDK handles payments, identity, vault, audit, and pricing.
Install it in Claude Code:
/plugin marketplace add lonniev/tollbooth-sample
/plugin install bootstrap-dpyc-operator@tollbooth-dpycThen ask Claude to "make my API a paid DPYC operator" — the skill activates automatically by
its description. It never touches your original code (it emits a sibling <slug>-mcp/ project)
and reads this repo's live wheel pin on every run, so it can't go stale.
See skills/bootstrap-dpyc-operator/ for the skill and its
reference guides (canonical pattern, source adapters, sessions & vaults, onboarding checklist).
Related MCP server: Boilerplate Paid MCP Server
The DPYC Economy
DPYC stands for Don't Pester Your Customer. It's a philosophy and protocol for API monetization that eliminates mid-session payment popups, subscription nag screens, and KYC friction.
How it works
Pre-funded balances — Users buy credits via Bitcoin Lightning before using tools. Each tool call silently debits from their balance. No interruptions, no "please upgrade" modals.
Nostr keypair identity — Users are identified by a Nostr public key (
npub), not an email or password. One keypair per role, managed by the user. No account creation forms.UUID-keyed tool identity — Every tool is a
ToolIdentityobject with a deterministic UUID v5 derived from a capability name. Pricing hints come from thecategoryfield:Category
Pricing hint
Use case
free0 sats
Balance checks, status
read1 sat
Simple lookups
write5 sats
Multi-step operations
heavy10 sats
Expensive queries
Actual prices are set dynamically by the operator's pricing model in Neon.
Rollback on failure — If the downstream API fails after a debit, credits are automatically rolled back via a compensating tranche. The user never pays for a failed call.
Social Contract — The DPYC ecosystem is a voluntary community bound by transparent, auditable economic rules, with a Certification Chain that cascades trust from the root:
Citizens — Users who consume API services
Operators — Developers who run MCP services (like this one)
Authorities — Certify operators and collect a small tax on purchases
First Curator — The root of the chain, mints the initial cert-sat supply
How Tollbooth Monetization Works
ToolIdentity and the frozen tool_id
Each domain tool is registered as a ToolIdentity with a frozen tool_id
(an opaque UUID), a capability name, a category (pricing hint), and an intent
description. Mint the UUID once at the tool's birth — run
capability_uuid("get_current_weather") at a REPL (or uuid.uuid4()), then
paste the result as a literal constant and never change it again. Freezing the
literal is what lets you rename a capability later without orphaning its pricing
rows in Neon. Do not call capability_uuid(...) at runtime; the identity
must live in exactly one place:
from tollbooth.tool_identity import ToolIdentity, STANDARD_IDENTITIES
from tollbooth.runtime import OperatorRuntime, register_standard_tools
from tollbooth.credential_templates import CredentialTemplate, FieldSpec
from tollbooth.credential_validators import validate_btcpay_creds
# Frozen UUIDs — minted once at tool birth, never recomputed.
GET_CURRENT_WEATHER_UUID = "b7327eb8-92b4-5252-84e0-ba3f437a16ed"
GET_WEATHER_FORECAST_UUID = "b6d0e596-3aec-5a62-980b-7875aa04d079"
GET_HISTORICAL_WEATHER_UUID = "5608f3e9-44c4-5b28-9744-704af6d701f0"
# 1. Define domain tool identities
_DOMAIN_TOOLS = [
ToolIdentity(
tool_id=GET_CURRENT_WEATHER_UUID,
capability="get_current_weather",
category="read",
intent="Get current weather conditions",
),
ToolIdentity(
tool_id=GET_WEATHER_FORECAST_UUID,
capability="get_weather_forecast",
category="write",
intent="Get weather forecast",
),
ToolIdentity(
tool_id=GET_HISTORICAL_WEATHER_UUID,
capability="get_historical_weather",
category="heavy",
intent="Get historical weather data",
),
]
TOOL_REGISTRY: dict[str, ToolIdentity] = {ti.tool_id: ti for ti in _DOMAIN_TOOLS}The @runtime.paid_tool() decorator
Every paid tool is a single decorator away from full DPYC monetization.
The decorator takes the tool's frozen tool_id constant and handles debit,
balance checks, constraint evaluation, rollback on failure, and low-balance
warnings automatically. Your tool function contains only domain logic:
from typing import Any
from fastmcp import FastMCP
from tollbooth.params import PatronNpub
mcp = FastMCP("tollbooth-sample", ...)
# Create the runtime with merged standard + domain identities
runtime = OperatorRuntime(
tool_registry={**STANDARD_IDENTITIES, **TOOL_REGISTRY},
operator_credential_template=CredentialTemplate(
service="tollbooth-sample-operator",
version=2,
description="Operator credentials for BTCPay Lightning payments",
fields={
"btcpay_host": FieldSpec(required=True, sensitive=True, ...),
"btcpay_api_key": FieldSpec(required=True, sensitive=True, ...),
"btcpay_store_id": FieldSpec(required=True, sensitive=True, ...),
},
),
credential_validator=validate_btcpay_creds,
# Connections prove the patron's npub (NIP-98 signed requests or an
# OAuth holder connection) against this host.
holder_auth_url="https://tollbooth-sample.fastmcp.app",
...
)
# Delegate all standard DPYC tools to the wheel.
# register_standard_tools returns the slug-prefixed @tool decorator —
# use it for the operator's own paid tools below.
tool = register_standard_tools(mcp, "weather", runtime, ...)
# Decorate each paid domain tool
@tool
@runtime.paid_tool(GET_CURRENT_WEATHER_UUID)
async def current(
latitude: float,
longitude: float,
npub: PatronNpub = "",
) -> dict[str, Any]:
"""Get current weather conditions for a location.
Returns temperature, wind speed, and weather code from Open-Meteo.
"""
return await weather.get_current(latitude, longitude)That is the complete paid tool. No manual debit calls, no try/except rollback blocks, no balance-warning plumbing. The decorator:
Looks up the tool's pricing from the
ToolIdentityregistry by UUIDExtracts
npubfrom the function arguments for billingChecks that the connection proves that npub (a signed request, or an OAuth connection that holds it)
Debits before calling your function (walking the tool's constraint chain from the pricing model)
Rolls back automatically if your function raises an exception
Appends a low-balance warning to the response when funds are running low
Key patterns
register_standard_tools(mcp, "weather", runtime, …) — Registers all
standard DPYC tools (balance, purchase, payment, pricing, Secure Courier,
Oracle, constraints) from the tollbooth-dpyc wheel, mounts oracle
delegations under <slug>_oracle_*, and returns the slug-prefixed
@tool decorator. Capture the return so you can use the same decorator
for your own paid tools — every wire-exposed name on this operator then
shares one slug prefix.
validate_btcpay_creds — Credential validator that checks BTCPay
credentials at receive time, not at first use. Invalid credentials are
rejected immediately during the Secure Courier exchange.
CredentialTemplate — Declares the operator's required secrets
(BTCPay host, API key, store ID) so the Secure Courier flow can prompt
for the right fields and validate them on delivery.
The npub parameter
Every paid tool must accept an npub keyword argument. It tells the runtime
which patron to bill; the connection proves the caller holds it. Use the SDK's
PatronNpub type so every operator describes it the same way:
from tollbooth.params import PatronNpub
npub: PatronNpub = ""A paid tool called with an empty or invalid npub is refused (npub is required)
before your function runs.
What the runtime handles under the hood
Tool call arrives
|
v
@runtime.paid_tool(GET_CURRENT_WEATHER_UUID)
|
+-- UUID lookup in tool_registry -> ToolIdentity + pricing
+-- npub extraction from kwargs; the connection proves it
|
+-- Constraint chain from the pricing model (discounts, surge, supply caps, coupons)
+-- Balance check + debit
| |
| insufficient --> Return error (no function call)
|
+-- Call your function
| |
| exception --> Automatic rollback, return error
|
+-- Append low-balance warning if needed
|
v
Return result to callerConstraint Engine
Constraints are dynamic pricing steps that live in the operator's pricing model:
each tool's chain in the model lists the steps the ConstraintGate walks on every
call, and coupons bound to the tool are added after them. Author them in
Pricing Studio or with
weather_set_pricing_model; nothing is switched on by environment variable.
Common constraint types (the SDK registry holds more — weather_list_constraint_types
enumerates the full set live):
Type | Effect |
| First N calls are free |
| Discount during specific hours |
| Allow calls only during a time window |
| Cap total invocations globally |
| Discount after spending N sats |
| Discount after N invocations |
| Demand-elastic multiplier during high demand |
Use weather_check_price to preview constraint effects without spending credits —
it walks exactly the chain the debit will.
Becoming an Operator
New to Tollbooth? See GETTING-STARTED.md for a step-by-step guide covering Nostr keypair setup, Authority enrollment, BTCPay configuration, and deploying your first monetized MCP service.
Quick Start
Local development
git clone https://github.com/lonniev/tollbooth-sample.git
cd tollbooth-sample
pip install -e ".[dev]"
python -m tollbooth_sample.serverThis serves over STDIO. There is no development bypass: paid tools are gated exactly as in production, and the patron's npub is proven by the HTTP connection (a NIP-98 signed request or an OAuth holder bearer), so over STDIO a paid tool is refused. Exercise paid tools against a deployed instance.
Deploy on Prefect Horizon
The hosting platform is Prefect Horizon (FastMCP is the runtime/framework the server is built on).
Push to GitHub
Connect the repo on Prefect Horizon
Set environment variables:
TOLLBOOTH_NOSTR_OPERATOR_NSEC— Nostr key for identity bootstrap (the only env var the operator needs; the Neon database URL arrives from your Authority over Nostr, the relay set comes from the shared dpyc-community registry, and all other secrets are delivered via Secure Courier credential templates)
Horizon reads the entrypoint and dependencies from fastmcp.json.
Heads-up for operators with long-running tools. By default, claim-check / async jobs run in-memory (
async_jobs.backend: "memory (default)"), which means they do not survive a Horizon recycle (durable_across_recycles: false). That's fine for this reference sample, which has no long-runners — but if you add a tool that defers work to a background job, pin the tollbooth-dpyc[modal]extra, spreadLONGRUNNER_CREDENTIAL_FIELDSinto your operator credential template, and deliver the durable-executor secrets (modal_token_id/modal_token_secret/modal_app_name) via Secure Courier so jobs settle across redeploys. Check your live state anytime withservice_status.async_jobs.
Run tests
pip install -e ".[dev]"
pytest -vTool Reference
MCP tool name | Cost | Description |
| read | Current weather for lat/lon |
| write | Multi-day forecast (1-16 days) |
| heavy | Historical weather for a date range |
| free | Check credit balance |
| free | Buy credits via Lightning |
| free | Check invoice status |
| free | Request adoption by an Authority (deferred-courtship onboarding) |
| free | Preview cost (shows constraint effects) |
| free | Health + constraint config summary |
| free | DPYC onboarding instructions |
| free | Current certification tax rate |
| free | Look up a DPYC member |
| free | DPYC ecosystem description |
| free | Active network advisories |
The three weather tools are this operator's own; the rest come from
register_standard_tools() and include identity (weather_request_npub_proof,
weather_receive_npub_proof), Secure Courier, pricing, coupons, and notarization
tools. weather_get_operator_onboarding_status reports what is still missing.
DPYC Ecosystem
Core
tollbooth-dpyc — Python SDK (vault, auth, pricing, Lightning, Nostr identity)
dpyc-community — Governance registry: membership, advisories, threat model
dpyc-oracle — Community concierge (free onboarding + member lookup)
tollbooth-authority — Certification backbone (Schnorr-signed certificates)
tollbooth-sample — Sample Operator (this canonical template)
tollbooth-pricing-studio — iOS pricing-model editor / operator console
Operators
cypher-mcp — Monetized graph answers: named Cypher templates over Neo4j/AuraDB
schwab-mcp — Charles Schwab brokerage data
thebrain-mcp — TheBrain personal knowledge graph
excalibur-mcp — X/Twitter posting
taxsort-mcp — Tax classification + Cloudflare Pages UI
optionality-mcp — Options analytics (brokerage-data operator)
goodearth-mcp — Climate analytics for small specialty-crop farms
beesknees-mcp — The Bee's Knees, a monetized multiplayer race game
roastify-mcp — Roastify coffee catalog and packaging artwork
ChartRemotely-mcp — Puts a security on a desktop chart, by voice or tool call
Advocates & utilities
tollbooth-oauth2-collector — OAuth2 callback handler (advocate service)
tollbooth-shortlinks — URL shortener utility
tollbooth-web — Shared browser SDK for operator front ends
License
Apache-2.0
This server cannot be deployed
Maintenance
Related MCP Connectors
Hosted MCP server for Xweather weather data: conditions, forecasts, alerts, and more.
Open-Meteo MCP — weather forecast + historical reanalysis + sister APIs
Open-Meteo tabanlı anahtarsız hava durumu tahmin MCP sunucusu.
Pay-per-action access to APIs and MCP tools over Lightning L402 and Base USDC x402.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMinimal MCP server demonstrating L402 pay-per-call with Depth-of-Identity reputation gating, providing a bitcoin data tool that fetches BTC price and mempool fees.MIT
- AlicenseNot gradedqualityDmaintenanceA boilerplate MCP server demonstrating paid tools via Lightning micropayments, including weather data and food ordering.4Apache 2.0
- AlicenseNot gradedqualityDmaintenanceMCP Server for global weather, forecasts, air quality, and climate data using Open-Meteo, no API key required.22 PyPIMIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that wraps the Open-Meteo API to provide current weather, forecasts, and historical data for any location without requiring an API key.MIT