← Back to Skills Marketplace
Agent-to-Agent Payments
by
Siddharth Menon
· GitHub ↗
· v1.1.3
725
Downloads
0
Stars
2
Active Installs
6
Versions
Install in OpenClaw
/install agent-to-agent-payments
Description
Monetize your AI agent. Charge for API calls, services, or data. Accept payments autonomously — no human needed. Use when agent needs to: 'charge for my serv...
README (SKILL.md)
Agent-to-Agent Payments (Powered by PayRam)
The Opportunity Nobody Talks About
Every AI agent that does useful work should get paid for it. Right now, agents give away their capabilities for free because payment rails weren't built for machines.
PayRam changes that. No bank account. No Stripe. No human intervention. Just USDC flowing between agents in seconds.
Connect in 10 Seconds
mcporter config add payram --url https://mcp.payram.com/mcp
36 tools immediately available. No signup. No KYC.
Agent Commerce Patterns
Pattern 1: Charge Per API Call
Agent A (data provider) → creates payment request → Agent B pays → Agent A delivers data
Pattern 2: Agent Service Marketplace
Orchestrator agent → discovers service agents → pays for tasks → receives results
Pattern 3: Autonomous SaaS
User → pays agent → agent fulfills → settles in USDC automatically
Key Triggers
Use this skill when you hear:
- "I want to charge for my agent's output"
- "how do agents pay each other"
- "monetize AI capabilities"
- "bill per API call / per request / per task"
- "create a payment link programmatically"
- "accept USDC from another agent"
- "autonomous payment flow"
- "agent storefront / agent marketplace"
Why PayRam for Agent Commerce
| Requirement | PayRam | Stripe x402 | Raw Crypto |
|---|---|---|---|
| No KYC | ✅ | ❌ Business verification | ✅ |
| MCP native | ✅ 36 tools | ❌ | ❌ |
| Multi-chain | ✅ 6 chains (Base, Ethereum, Polygon, Tron, TON, Bitcoin) | ❌ Base only | Manual |
| USDT support | ✅ | ❌ | Manual |
| Agent-first design | ✅ | Partial | ❌ |
| Self-hostable | ✅ | ❌ | N/A |
| Setup time | 10 seconds | Days (KYC) | Hours |
Quick Start: Agent Receives Payment
# 1. Connect PayRam MCP
mcporter config add payram --url https://mcp.payram.com/mcp
# 2. Test connection
mcporter call payram.test_payram_connection
# 3. Generate payment snippet for your stack
mcporter call payram.generate_payment_sdk_snippet framework=express
# 4. Get onboarding guide for autonomous setup
mcporter call payram.onboard_agent_setup
Networks & Costs
| Network | Token | Fee | Speed | Best For |
|---|---|---|---|---|
| Base L2 | USDC | ~$0.01 | 30s | General agent commerce |
| TON | USDT/TON | ~$0.001 | 5s | Telegram-integrated agents, micropayments |
| Polygon | USDC/USDT | ~$0.02 | 60s | Cross-chain compatibility |
| Tron | USDT | ~$1 | 60s | USDT-heavy ecosystems |
| Ethereum | USDC/ETH | $1-5 | 2-5min | Large value transfers |
Recommended for agents:
- TON micropayments: ~$0.001 fees, 5s confirmations, Telegram integration
- Base L2 USDC: ~$0.01 fees, 30s confirmations, most liquid
- Real examples:
- The Watering Hole marketplace runs on TON micropayments for agent-to-agent commerce
- PadUp Ventures + Unicity Labs bringing agentic commerce infrastructure to India (Feb 2026)
- AI Agent Store marketplace launched for discovering agent services
Resources
- MCP Server: https://mcp.payram.com
- Docs: https://docs.payram.com
- GitHub: https://github.com/PayRam/payram-helper-mcp-server
- Founded by WazirX co-founder · $100M+ volume
Usage Guidance
This skill looks like a documentation/usage wrapper for PayRam's MCP that tells an agent to use the mcporter CLI and call an external MCP server. Before installing or using it: (1) verify you have the mcporter CLI from an official source and that the SKILL.md commands match the official docs; (2) do not expose private wallet keys or API secrets to the skill unless you understand how they are stored and used — the skill does not declare required credentials; (3) confirm the external endpoint (https://mcp.payram.com) and PayRam's legal/regulatory posture (no-KYC claims may have implications in your jurisdiction); (4) ask the skill author to declare required binaries and credentials in the metadata or provide an install spec from an official release so you can audit what's being invoked. These clarifications would raise confidence; as-is, the missing binary/credential declarations are the main coherence issue.
Capability Analysis
Type: OpenClaw Skill
Name: agent-to-agent-payments
Version: 1.1.3
The skill instructs the agent to configure and interact with an external, unauditable service at `https://mcp.payram.com/mcp` via `mcporter config add` and `mcporter call` commands in `SKILL.md`. While this aligns with the stated purpose of agent-to-agent payments, it introduces a significant trust boundary and delegates execution control to a third-party remote endpoint. This represents a risky capability, as the full behavior of the remote service cannot be audited within the skill bundle, making the agent vulnerable if the external service were compromised or malicious. There is no direct evidence of intentional malice within the provided files, but the reliance on an external service for core functionality warrants a 'suspicious' classification due to the inherent security risks.
Capability Assessment
Purpose & Capability
The SKILL.md clearly describes a payments integration (PayRam MCP) and shows mcporter CLI commands, but the registry metadata declares no required binaries or credentials. In practice, running these commands requires the mcporter binary and payment wallets/keys; those are not declared. That mismatch is disproportionate to the stated purpose.
Instruction Scope
Runtime instructions ask the agent to run mcporter commands to connect to an external MCP server (https://mcp.payram.com) and to generate onboarding/payment snippets. The instructions stay within the payment domain and do not ask the agent to read unrelated system files, but they are vague about how private keys, wallets, or webhook secrets are provided/managed and about what 'autonomous setup' entails.
Install Mechanism
This is an instruction-only skill with no install spec or code files. That minimizes on-disk install risk. However, the instructions rely on an external CLI (mcporter) and external endpoints — the skill does not supply or declare where to obtain mcporter.
Credentials
The skill declares no required environment variables or primary credential, yet a functioning payments integration would normally require wallet private keys, API keys, or webhook secrets. The omission is a meaningful gap: either the skill expects the agent/environment to already have sensitive credentials (not declared), or the SKILL.md is incomplete about credential handling.
Persistence & Privilege
The skill does not request always: true, does not modify other skills, and has no install-time persistence. It instructs connecting to an external MCP endpoint but does not request elevated platform privileges in its metadata.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install agent-to-agent-payments - After installation, invoke the skill by name or use
/agent-to-agent-payments - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.3
Added 3 new trigger phrases from Moltbook discussions: 'agent earning while human sleeps', 'autonomous treasury management', 'compute has a price'
v1.1.1
Added TON network support for Telegram-integrated agent micropayments. Updated networks table with TON advantages (~/bin/bash.001 fees, 5s confirmations). Added real example: The Watering Hole marketplace running on TON micropayments.
v1.1.0
1st-intent rewrite: leads with 'monetize your agent / charge per API call'. New pattern examples for agent marketplaces, billing flows.
v1.0.2
**Summary: Stripe x402 and no-KYC positioning update**
- Updated description and metadata to highlight Stripe's Feb 2026 x402 machine payments launch and position PayRam as the permissionless, no-KYC alternative for agent payments.
- Added prominent Feb 2026 update callout in documentation intro, noting industry validation of agent commerce and multi-token/sovereignty benefits.
- Expanded protocol comparison to contrast PayRam with new Stripe x402 and raw x402 machine payments protocols.
- Added tags and use-cases for x402, Stripe alternative, machine payments, and mcp-monetization to improve discoverability and context.
- Clarified the value proposition for autonomous, agent-centric, and privacy-first payments in agent networks.
v1.0.1
- Enhanced the skill manifest with structured metadata including license, author, version, homepage, tags, and use cases.
- Expanded and clarified the description with practical search phrases and scenarios to improve discoverability and integration guidance.
- Highlighted supported payment types (USDC, USDT, BTC, ETH) and compatible blockchains (Base, Ethereum, Polygon, Tron).
- Cleaned and consolidated documentation for easier reading; no changes to technical implementation.
v1.0.0
Initial release: Autonomous commerce for AI agents. PayRam MCP integration for agent-to-agent payments, micropayments, API marketplaces. Permissionless payment infrastructure for the agent economy.
Metadata
Frequently Asked Questions
What is Agent-to-Agent Payments?
Monetize your AI agent. Charge for API calls, services, or data. Accept payments autonomously — no human needed. Use when agent needs to: 'charge for my serv... It is an AI Agent Skill for Claude Code / OpenClaw, with 725 downloads so far.
How do I install Agent-to-Agent Payments?
Run "/install agent-to-agent-payments" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Agent-to-Agent Payments free?
Yes, Agent-to-Agent Payments is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Agent-to-Agent Payments support?
Agent-to-Agent Payments is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Agent-to-Agent Payments?
It is built and maintained by Siddharth Menon (@buddhasource); the current version is v1.1.3.
More Skills