monospay-mcp
Pay per MCP tool call in USDC on Base. Non-custodial settlement, no admin keys, 30 bps fee.
README
monospay
Your AI agent can send payments.
pip install monospay · Your agent can pay.
Get started
Claude Desktop — paste into your config, done:
{
"mcpServers": {
"monospay": {
"command": "npx",
"args": ["-y", "monospay-mcp"],
"env": { "MONO_API_KEY": "mono_live_..." }
}
}
}
Restart Claude Desktop. Ask: "Check my monospay balance"
Ready to move money? Add your private key:
{
"mcpServers": {
"monospay": {
"command": "npx",
"args": ["-y", "monospay-mcp"],
"env": {
"MONO_API_KEY": "mono_live_...",
"MONO_PRIVATE_KEY": "0x..."
}
}
}
}
Then ask: "Send $1.00 to 0x..."
| With API key only | + Private Key |
|---|---|
| ✅ Check balance | ✅ Check balance |
| ✅ View transactions | ✅ View transactions |
| ✅ Set spending limits | ✅ Set spending limits |
| ❌ Send payments | ✅ Send payments |
Claude Code — one command:
claude mcp add monospay -e MONO_API_KEY=mono_live_... -- npx -y monospay-mcp
Python SDK — 3 lines of code:
pip install monospay
from mono_sdk import MonoClient
client = MonoClient(api_key="mono_live_...")
client.signed_transfer(to_wallet="0x...", amount=1.00, private_key="0x...")
Dashboard — no code, manage everything in your browser:
monospay.com/dashboard
Get your API key at monospay.com/dashboard → Agents → Issue API key.
Why monospay
- 10 minutes to first payment — paste config or pip install, your agent pays
- Works with every AI framework — LangChain, CrewAI, OpenAI, Claude, Cursor, Google ADK
- Sub-cent transactions — no $0.30 minimum like card networks
- Agents don't need bank accounts — just a wallet and a private key
- You stay in control — spending limits, daily budgets, transaction history
Python SDK — Quickstart
from mono_sdk import MonoClient
# Each agent has its own API key (from dashboard -> Agents -> Issue API key)
agent_a = MonoClient(api_key="mono_live_...")
# Agent A checks its balance
balance = agent_a.balance()
print(f"Budget: ${balance['available_usdc']}") # -> Budget: $50.00
# Agent A pays Agent B
result = agent_a.signed_transfer(
to_wallet="0x...",
amount=1.50,
private_key="0x...",
)
print(result["transaction_id"])
No wallets to manage. No gas. No KYC.
2-Agent Example
from mono_sdk import MonoClient
agent_a = MonoClient(api_key="mono_live_A...")
agent_b = MonoClient(api_key="mono_live_B...")
# Agent A pays Agent B
agent_a.signed_transfer(
to_wallet="0xAgentB_Wallet",
amount=0.50,
private_key="0xAgentA_Key",
)
print(f"A balance: ${agent_a.balance()['available_usdc']}")
print(f"B balance: ${agent_b.balance()['available_usdc']}")
CLI — for developers
The CLI lets you inspect and manage your agents from the terminal.
mono balance # Show your agent's balance
mono health # Check gateway status
mono config show # Show current config
LangChain
pip install "monospay[langchain]"
from mono_sdk.langchain_tools import MonoToolkit
toolkit = MonoToolkit(api_key="mono_live_...")
tools = toolkit.get_tools()
OpenAI Function Calling
from mono_sdk.openai_functions import get_mono_tools, handle_tool_call
tools = get_mono_tools()
# Pass tools to your OpenAI chat completion
Error handling
from mono_sdk.errors import InsufficientBalanceError, AuthenticationError
try:
agent_a.signed_transfer(to_wallet="0x...", amount=999.00, private_key="0x...")
except InsufficientBalanceError:
print("Out of budget — top up at monospay.com/dashboard")
except AuthenticationError:
print("Invalid key — run: mono init")
Links
- Dashboard · monospay.com
- Docs · monospay.com/docs
- PyPI · monospay
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.