mcpField
A
agentpay

agentpay

Local
github.com/sdeanesh-pngFinance

About agentpay

Spending controls for AI agents: per-agent budgets, vendor allowlists, full audit trail.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"sdeanesh-png-agentpay": {
"command": "npx",
"args": [
"-y",
"@agentpay-run/mcp-server"
],
"env": {
"AGENTPAY_API_KEY": "<AGENTPAY_API_KEY>",
"AGENTPAY_BASE_URL": "<AGENTPAY_BASE_URL>"
}
}
}
}
Run commandnpx -y @agentpay-run/mcp-server
Environment variables to set
AGENTPAY_API_KEYSecretAgentPay wallet API key (ap_test_... or ap_live_...). Generate at https://agentpay.run/dashboard.
AGENTPAY_BASE_URLOverride for self-hosted or local dev. Defaults to https://agentpay.run.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@agentpay-run/mcp-server0.2.1

Tools

4

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
vendorstringYesVendor identifier. Domain form preferred ('openai.com', 'stripe.com'). Used for vendor allowlist matching and audit logs.
metadataobjectNoOptional free-form metadata stored on the transaction. Useful for tagging the agent run / task that triggered the charge.
amount_centsintegerYesAmount in USD cents. e.g. 1200 = $12.00. Must be a positive integer.
idempotency_keystringNoOptional key to prevent double-charging on retries. Re-sending the same key + wallet returns the prior result instead of creating a new charge.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.