sipi.bot — Spend Firewall for AI Agents

io.github.kindrat86Published by GitHub account kindrat86v1.0.1Updated Oct 24, 2026

Pre-spend firewall for AI agents. Approves, blocks, flags transactions against policy rules.

VerifiedStreamable HTTPWeb executableFinanceSecurity & Monitoring

Overview

AI-generated overview

Lets an assistant check proposed transactions against policy rules before spending, approving, blocking, or flagging them.

What you can do
This remote MCP server acts as a pre-spend firewall for AI agents. According to its description, it approves, blocks, or flags transactions against policy rules. No individual tools are listed in the supplied material.
When to use it
Worth considering when an assistant can initiate or propose payments or other transactions and you want a policy check before the money moves. It is aimed at teams that need a consistent approve, block, or flag decision on agent-initiated spending.
Requirements
Runs as a remote streamable HTTP endpoint at No packages, environment variables, or headers are declared, and no authentication is declared in the manifest.
Before you install
The description says it approves, blocks, and flags transactions, so it can affect whether spending proceeds; treat its decisions as a control point and review the policy rules before relying on it. No authentication method, credentials, or data handling are documented in the supplied material, so verify what transaction details are sent to the remote endpoint before use.

Installation

In SourceWeft

  1. Open sipi.bot — Spend Firewall for AI Agents 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/io.github.kindrat86%2Fsipi-bot-spend-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": {
    "sipi-bot-spend-firewall-for-ai-agents": {
      "type": "http",
      "url": "https://sipi.bot/api/mcp"
    }
  }
}

Tools

3

evaluate_spend

Check whether an autonomous agent is allowed to make a purchase BEFORE spending. Returns APPROVED, BLOCKED, or FLAGGED.

Parametersamountrequiredcategorymerchantdescription

add_spend_rule

Add a rule to the authenticated API key's isolated workspace.

Parameterslabelactionparamsrequiredpriorityrule_typerequired

firewall_status

Get private firewall stats for the authenticated API key.

Takes no parameters.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

83% 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
  • 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.