Agent Commerce Payments MCP
This server exposes five agent-to-agent commerce/payment tools that generate structured invoice, payment, escrow, and history outputs in-memory (descriptions claim read-only, no-side-effect, idempotent behavior).
create_invoice — build itemized invoices with tax, fees, currency (default GBP), and payment terms (due_days).
process_payment — simulate payment processing for an invoice, including fraud checks, fee calculation, and settlement (default method
agent_balance).escrow_funds — set up conditional escrow between two agents with amount, currency, release condition, and expiry (default 72h).
release_escrow — release escrowed funds to a recipient agent with a stated reason, after condition verification.
payment_history — retrieve an agent's transaction history with status filtering, limits, and totals.
Notes: tools require no auth for basic use, accept an optional api_key (or MEOK_API_KEY), and are rate-limited to 10 calls/day on free tier. Despite names implying money movement, all tools are described as producing computed output only, so treat results as reports/simulations rather than real fund transfers.
Provides integration with Stripe for payment processing, enabling product catalog, cart, checkout, and order tracking with multi-currency support.
Agent Commerce Payments MCP
Agent commerce protocol MCP — product catalog, cart management, checkout, order tracking
Agent commerce protocol MCP — product catalog, cart management, checkout, order tracking. MIT.
🚀 Quick Start
# Install via pip
pip install agent_commerce_payments_mcp
# Or install via Smithery
npx -y @smithery/cli@latest install agent-commerce-payments-mcp --client claudeRelated MCP server: Ecommerce AI MCP
✨ Features
Product catalog management
Cart & checkout
Stripe integration
x402 protocol support
Multi-currency
📖 Documentation
🛡️ Compliance
This MCP server is built with EU AI Act compliance built-in:
✅ Article 9 — Risk Management System
✅ Article 13 — Transparency & Instructions for Use
✅ Article 15 — Bias Detection & Testing
✅ Article 26 — FRIA Support (where applicable)
✅ Article 50 — AI Content Watermarking (where applicable)
Need help getting compliant? Book a free 15-min diagnostic →
How MEOK charges
MEOK has no subscriptions and no tiers. You pay per job, and only when the agreed artifact has been delivered to you. There is no public price list. See https://meok.ai/pricing.
This repository's source is MIT-licensed and free to self-host.
🤝 Part of the MEOK Ecosystem
This server is part of the MEOK AI Labs ecosystem — 300+ MCP servers for sovereign AI governance.
Domain | Purpose |
EU AI Act compliance marketplace | |
AI safety & monitoring | |
Sovereign AI platform | |
Legacy modernization |
📜 License
MIT © CSOAI-ORG
Configuration
Add to your claude_desktop_config.json (Claude Desktop) or your MCP client config:
{
"mcpServers": {
"agent-commerce-payments-mcp": {
"command": "uvx",
"args": ["agent-commerce-payments-mcp"]
}
}
}Or: pip install agent-commerce-payments-mcp then run the agent-commerce-payments-mcp command (stdio transport).
Examples
Once configured, ask your assistant, for example:
"Use
create_invoiceto …""Use
process_paymentto …""Use
escrow_fundsto …"
Available Tools
5 toolscreate_invoiceDInspect
Create a detailed invoice with line items, tax calculation, fees, and payment terms.
Behavior: This tool generates structured output without modifying external systems. Output is deterministic for identical inputs. No side effects. Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.
When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results.
Args: from_agent (str): The from agent to analyze or process. to_agent (str): The to agent to analyze or process. amount (float): The amount to analyze or process. currency (str): The currency to analyze or process. description (str): The description to analyze or process. line_items (list): The line items to analyze or process. due_days (int): The due days to analyze or process. api_key (str): The api key to analyze or process.
Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.
Inputs: amount (required), to_agent (required), from_agent (required), api_key, +4 more. Returns: result
escrow_fundsDInspect
Place funds in escrow between two agents with conditions and expiry.
Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.
When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results.
Args: agent_a (str): The agent a to analyze or process. agent_b (str): The agent b to analyze or process. amount (float): The amount to analyze or process. currency (str): The currency to analyze or process. condition (str): The condition to analyze or process. expiry_hours (int): The expiry hours to analyze or process. api_key (str): The api key to analyze or process.
Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.
Inputs: amount (required), agent_a (required), agent_b (required), api_key, +3 more. Returns: result
payment_historyAInspect
Get payment history for an agent with filtering, totals, and transaction summary.
Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.
When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results.
Args: agent_id (str): The agent id to analyze or process. status_filter (str): The status filter to analyze or process. limit (int): The limit to analyze or process. api_key (str): The api key to analyze or process.
Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.
Inputs: agent_id (required), limit, api_key, status_filter. Returns: result
process_paymentCInspect
Process payment for an invoice with fraud checks, fee calculation, and settlement.
Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.
When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results.
Args: invoice_id (str): The invoice id to analyze or process. payment_method (str): The payment method to analyze or process. api_key (str): The api key to analyze or process.
Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.
Inputs: invoice_id (required), api_key, payment_method. Returns: result
release_escrowDInspect
Release escrowed funds to the designated agent after condition verification.
Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.
When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results.
Args: escrow_id (str): The escrow id to analyze or process. to_agent (str): The to agent to analyze or process. release_reason (str): The release reason to analyze or process. api_key (str): The api key to analyze or process.
Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.
Inputs: to_agent (required), escrow_id (required), api_key, release_reason. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Tool names are distinct (create_invoice, escrow_funds, etc.), but the descriptions are nearly identical and contain contradictory claims about being read-only, which could confuse an agent trying to differentiate their actual capabilities.
Most tools use a verb_noun pattern, but payment_history breaks this pattern with a noun_noun structure, indicating minor inconsistency.
With 5 tools covering invoicing, escrow, payment processing, and history, the count is well-scoped for a payments MCP server.
The descriptions claim all tools are read-only and stateless, which fundamentally contradicts the expected actions of creating invoices, processing payments, and managing escrow, leaving major gaps in a realistic payments workflow.
Maintenance
Related MCP Connectors
Agent Orchestrator MCP Server by MEOK AI Labs
Agent Negotiation MCP Server by MEOK AI Labs
Agent Delegation MCP Server by MEOK AI Labs
Agent Commerce Protocol MCP — bridges Stripe ACP + Google AP2 + Coinbase x402 for agent payments
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceMCP server for AgentPay — the payment gateway for autonomous AI agents. Fund a wallet once, give your agent the key, and it discovers, provisions, and pays for tool APIs on its own. One key, every tool.112 npm1MIT
- AlicenseNot gradedqualityCmaintenanceEcommerce AI - MCP server providing AI-powered tools and automation by MEOK AI Labs3 npm50 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceAgent Identity Trust - MCP server providing AI-powered tools and automation by MEOK AI Labs10 npm158 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceAgent Negotiation - MCP server providing AI-powered tools and automation by MEOK AI Labs7 npm169 PyPIMIT