Agent Spend Policy Mcp

io.github.dingdawgPublished by GitHub account dingdawgv0.1.1Updated Oct 25, 2026

Local agent spend-policy checks. No funds, keys, payment authority, or network access.

VerifiedSTDIODesktop onlyFinanceDeveloper Tools

Overview

AI-generated overview

A local MCP server that checks a proposed agent spend action against a supplied policy and returns ELIGIBLE, DENY or STEP_UP with a reason code.

What you can do
Evaluate a proposed spend action against a supplied policy, given an evaluation time, the action and the already-spent amount in integer micro-unit strings, and get back one of ELIGIBLE, DENY or STEP_UP with a stable reason code. The check is deterministic and local, with no side effects, so it works as dry-run evidence before any payment step.
When to use it
Use it when an assistant needs a local, deterministic policy check on a proposed spend action, for example to gate or dry-run spending decisions before a separate payment system acts. It is not a payment or accounting system.
Requirements
Runs as a local stdio process on the desktop, started with npx from the npm package. No accounts, API keys, environment variables or headers are declared, and it makes no network requests.
Before you install
ELIGIBLE is local policy evidence only, not payment authorization. The caller supplies the clock and already-spent amount, so results are only as trustworthy as those inputs. It holds no funds, keys or payment credentials and does not sign, send or settle payments; a production payment adapter needs separate controls.

Installation

In SourceWeft

  1. Open Agent Spend Policy Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

DingDawg Agent Spend Policy MCP

A small, local MCP server that deterministically evaluates whether a proposed agent spend action matches a supplied policy.

It returns one of ELIGIBLE, DENY, or STEP_UP, with a stable reason code. ELIGIBLE is local policy evidence only. It is not payment authorization.

Safety boundary

This package does not hold funds, private keys, payment credentials, customer data, or settlement authority. It does not sign, send, settle, custody, or record payments. It makes no network requests.

A production payment adapter needs separate, independently verified controls for authenticated policy/action provenance, canonical payload hashing, durable atomic budget reservation and replay protection, customer-controlled signing, rail validation, and settlement reconciliation.

Install

bash
npx -y @dingdawg/agent-spend-policy-mcp

Configure it as a local stdio MCP server:

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

Tool

evaluate_spend_policy accepts an evaluation time, a policy, a proposed action, and the already-spent amount. All money is passed as integer micro-unit strings, never JavaScript floating-point numbers.

The caller supplies the clock and already-spent value; therefore this tool is safe for dry runs and local evidence, not a replacement for a trusted payment or accounting system.

Agent contract

The versioned machine-readable contract is capabilities.json. It describes the only tool this package exposes, its required inputs, its three possible outcomes, and its non-negotiable safety boundary.

  • Transport: local stdio MCP
  • Tool: evaluate_spend_policy
  • Required inputs: evaluationTime, policy, action, and alreadySpentMicros
  • Outputs: ELIGIBLE, DENY, or STEP_UP, each with a stable reason code
  • Side effects: none
  • Credentials, payment execution, custody, signing, settlement, and network access: not supported

The manifest is package-source evidence for this release, not a promise of a hosted agent-discovery endpoint. ELIGIBLE remains local policy evidence only, not payment authorization.

Development

bash
npm installnpm testnpm run pack:check

Source: README.md at commit 8e959c2

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% 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 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts