Agent Reserve Protocol Authorization Firewall

site.chatgpt.super-myna-7255.agent-reserve-protocolPublished by agent-reserve-protocol.super-myna-7255.chatgpt.siteOfficial publisherv0.1.0Updated Oct 24, 2026

Advisory policy preflight for AI-agent spend requests; never executes payments or accesses wallets.

VerifiedStreamable HTTPWeb executableFinanceSecurity & Monitoring

Overview

AI-generated overview

Remote MCP endpoint that gives an assistant one advisory check on AI-agent spend requests, returning eligible, escalate, or block under an owner-defined…

What you can do
  • Evaluate a proposed agent spend request against an owner-defined mandate and get back one of three verdicts: eligible, escalate, or block.
  • Use the verdict as a preflight policy check before an agent proceeds with a payment decision.
When to use it
Useful when an AI agent proposes spending money and you want a policy opinion on whether the request fits the owner's mandate before anything happens. It is a preflight check only, so it suits teams that already have a separate payment path and want a gate in front of it.
Requirements
A remote streamable HTTP endpoint; no package, environment variables, or headers are declared. No authentication is declared, so no account or API key setup is described.
Before you install
The verdict is advisory only: the server does not execute payments or access wallets, so it does not itself stop spending. No authentication is declared, so consider who can reach the endpoint and what spend details you send to it.

Installation

In SourceWeft

  1. Open Agent Reserve Protocol Authorization Firewall in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/site.chatgpt.super-myna-7255.agent-reserve-protocol%2Fagent-transaction-firewall/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "agent-reserve-protocol-authorization-fir": {
      "type": "http",
      "url": "https://agent-reserve-protocol.super-myna-7255.chatgpt.site/api/mcp"
    }
  }
}

Tools

1

evaluate_agent_spend_request

Evaluate agent spend request

Return eligible, escalate, or block under an owner-defined mandate. Advisory preflight only; never executes payment or accesses a wallet.

ParametersamountrequiredmandateValidrequiredvendorStatusrequiredreceiptStatusrequireddailyRemainingrequiredperRequestLimitrequired

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

72% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.