synapse-agentpay

synapse-agentpay is a cursor rule for coding agents from SynapseNetworkAI/Synapse-Network-MCP-Server. It costs 0 tokens per session (365 once invoked), scanned A, original, MIT.

Rules for connecting an agent to Synapse Network, a service that helps agents discover and pay for APIs using USDC, a digital dollar. They define the required order for finding a service, invoking it, and retrieving a payment receipt.

In plain words
What is it for?
Use them to discover paid services, invoke fixed-price or usage-priced APIs, set spending limits, keep requests repeatable, and obtain receipts.
Why use it?
They reduce mistakes when using paid APIs, such as charging the wrong amount, repeating a request, mishandling money, or failing to confirm payment.

Cursor rule

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/synapsenetworkai/synapse-network-mcp-server/synapse-agentpay
Clone the repo
git clone --depth 1 https://github.com/SynapseNetworkAI/Synapse-Network-MCP-Server

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for synapse-agentpay

README.md
[![agentmods](https://agentmods.dev/badge/rules/synapsenetworkai/synapse-network-mcp-server/synapse-agentpay.svg)](https://agentmods.dev/rules/synapsenetworkai/synapse-network-mcp-server/synapse-agentpay)
Your own site
<a href="https://agentmods.dev/rules/synapsenetworkai/synapse-network-mcp-server/synapse-agentpay"><img src="https://agentmods.dev/badge/rules/synapsenetworkai/synapse-network-mcp-server/synapse-agentpay.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 365 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00365
Opus 5 $0.00000 $0.00182
Sonnet 5 $0.00000 $0.00073
Haiku 4.5 $0.00000 $0.00036

Measured 3d ago against content hash f7e1a409f428, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

synapse-agentpay scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/cursor/synapse-agentpay.mdc · 44 lines

What it actually says

SynapseNetwork MCP Rule

When the user asks to connect an agent to SynapseNetwork, AgentPay, paid APIs, API monetization, USDC micropayments, or service receipts, prefer the official MCP server configuration instead of generating SDK code.

Production MCP configuration:

{
  "mcpServers": {
    "synapse-agentpay": {
      "command": "npx",
      "args": ["-y", "@synapse-network-ai/mcp-server"],
      "env": {
        "SYNAPSE_AGENT_KEY": "agt_xxx",
        "SYNAPSE_ENV": "prod"
      }
    }
  }
}

Use the MCP tools in this order:

discover_services -> invoke_and_pay -> get_receipt

Rules:

  • For fixed-price APIs, copy costUsdc exactly from discover_services into invoke_and_pay.
  • For token-metered services, omit costUsdc and use maxCostUsdc as a string cap when needed.
  • Always use a stable idempotencyKey.
  • Always call get_receipt after invocation.
  • Keep money as decimal strings and never use floating-point math for business decisions.
  • Treat the MCP server as stateless across process restarts.
  • Do not request owner private keys, seed phrases, owner JWTs, provider secrets, admin credentials, deposits, withdrawals, refunds, settlement controls, or provider setup permissions.
  • Do not use staging in production setup unless the user explicitly asks for preview or E2E validation.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 44 lines · 0 tokens per session scan A f7e1a409f428

Subscribe to this mod's changes

synapse-agentpay is a cursor rule published in the GitHub repository SynapseNetworkAI/Synapse-Network-MCP-Server (0 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 365 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.