Agent Spend Policy MCP server
Local agent spend-policy checks. No funds, keys, payment authority, or network access.
0 stars34 downloads/wk
Reviews
Write oneNobody has reviewed Agent Spend Policy yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Agent Spend Policy tools (1)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
evaluate_spend_policyDeterministically evaluates a proposed action against caller-supplied policy. This is local policy evidence only: it never authorizes, signs, sends, settles, custodies, or records a payment.
Public scan report
scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it
- Code scan7 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner7/10
How Agent Spend Policy compares
Against every graded Finance MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 91/100
- higher than 93% of 1,761 Finance servers
- Tools
- 1
- the typical Finance server has 8
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 34
- more than 25% of 421 Finance servers with a package
What its tools let an agent do: 1 run or deploy
Install Agent Spend Policy in Claude Code, Cursor or VS Code
Runs npx -y @dingdawg/agent-spend-policy-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add agent-spend-policy-mcp -- npx -y @dingdawg/agent-spend-policy-mcp
What the publisher says
From the Agent Spend Policy repository's README, as published. We do not edit it. Read it on GitHub
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 STEPUP, 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
npx -y @dingdawg/agent-spend-policy-mcpConfigure it as a local stdio MCP server:
{
"mcpServers": {
"dingdawg-agent-spend-policy": {
"command": "npx",
"args": ["-y", "@dingdawg/agent-spend-policy-mcp"]
}
}
}Tool
evaluatespendpolicy 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.
alreadySpentMicros
- Transport: local stdio MCP
- Tool: evaluatespendpolicy
- Required inputs: evaluationTime, policy, action, and
access: not supported
- Outputs: ELIGIBLE, DENY, or STEP_UP, each with a stable reason code
- Side effects: none
- Credentials, payment execution, custody, signing, settlement, and network
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
npm install
npm test
npm run pack:checkNothing above is checked by us. What we check is on the safety report.
Agent Spend Policy: common questions
- Is Agent Spend Policy MCP server safe?
- Yes, by our scan: it is graded A (91/100). Read the Agent Spend Policy safety report
- How do I install Agent Spend Policy?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Agent Spend Policy need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Agent Spend Policy maintained?
- The last commit was 42 days ago (2026-09-23). The latest release is v0.1.1.
- What can I use instead of Agent Spend Policy?
- Servers from other publishers that do the same job: Yolfi Payments MCP server, Boundra — Payment Approval Gateway for AI Agents MCP server and Pulsefeed X402 MCP server.
- How does Agent Spend Policy compare with other Finance MCP servers?
- safety score 91/100 (higher than 93% of 1,761 Finance servers); tools 1 (the typical Finance server has 8); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Agent Spend Policy
Same job from other publishers: the closest match first, then the best rated.
- Yolfi Payments MCPLet AI agents add Yolfi crypto checkout, paylinks, webhooks, and status checks.not reviewedEstablishedA
- Boundra — Payment Approval Gateway for AI AgentsAllow, ask, or veto — a policy decision point your agent consults before signing any paymentnot reviewedGrowingA
- Pulsefeed X402Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.not reviewedGrowingA
- three.ws Agent PaymentsGoverned x402 payment sessions: pay any endpoint with budget, allowlist & per-tx caps, no key.not reviewedEstablishedB
- X402 ListFind and vet x402 payment APIs before your agent pays one: uptime, price, on-chain volume.not reviewedEstablishedA