Agent Spend Policy Mcp

Overview

Agent Spend Policy Mcp is a Model Context Protocol server that performs local agent spend-policy checks without requiring funds, keys, payment authority, or network access. It integrates directly into AI assistants as a set of tools that models can invoke to enforce spending governance and policy controls.

The server runs entirely on your local machine via the npm package @dingdawg/agent-spend-policy-mcp and communicates with MCP clients over stdio. No authentication or credentials are needed—it operates out of the box. Version v0.1.1 is available under the MIT license, with source code hosted at DingDawg/dingdawg-agent-spend-policy-mcp on GitHub.

Agent Spend Policy Mcp is listed in the AI & Agents category on mcp.site and works with Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and other MCP clients. If you maintain this server, claim your listing to verify ownership, display the Verified badge, and ensure the information stays up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "agent_spend_policy_mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@dingdawg/agent-spend-policy-mcp"
      ]
    }
  }
}