mcpbeat Sign in

spendctl MCP Server

answering

spendctl is answering right now. Last checked 1 min ago. It exposes 8 tools.

Spend policy for AI agents that pay (x402, MPP). Login-free sandbox, real sidecar, no real funds.

Uptime history 15 days of history
15 days agonow
100.0%
Uptime 24h
92 of 92 checks
8
Tools
read from the server
301 ms
Response time
average over 24h
open, no key
Access
streamable-http

What changed 4

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 2 November 2026. No other catalogue keeps this.

5 Nov a tool description was rewritten sandbox_create
2 Nov 2 tools appeared await_approval, withdraw_approval
2 Nov a tool description was rewritten await_approval

Nothing serious here today

Today is the operative word: we check spendctl every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.

run in your terminal
claude mcp add spendctl --transport http https://mcp.spendctl.dev/mcp
Settings → Connectors → Add custom connector, then paste this address
https://mcp.spendctl.dev/mcp
~/.codex/config.toml
[mcp_servers.spendctl]
url = "https://mcp.spendctl.dev/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "spendctl": {
      "url": "https://mcp.spendctl.dev/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "spendctl": {
      "type": "http",
      "url": "https://mcp.spendctl.dev/mcp"
    }
  }
}

Available tools 8

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

sandbox
sandbox_create
Creates an isolated spendctl sandbox and returns its sandbox_id. Call it first: every other tool needs the sandbox_id, and one sandbox serves a whole conversation (create another only to try a different preset). The sandbox is a real spendctl sidecar with a throwaway wallet, a mock x402 facilitator and two mock paid APIs; no real money moves and nothing outside the sandbox is reachable. Returns the sandbox_id, the agent's policy (budgets, allowed hosts, approval rule) and the paid endpoints with their prices. Limits: 5 sandboxes per minute per client address (claude.ai users share addresses and get a larger allowance); a sandbox expires after 2 hours without calls (24 hours at most). Example: preset "strict" to see refusals, "approvals" to see a payment held for a human.
sandbox_pay
Fetches one of the sandbox's paid endpoints (HTTP 402, x402) through the spendctl sidecar, which applies the sandbox agent's budget, allowlist and approval policy, pays with the throwaway wallet if allowed, and returns the response. Use it for every paid call in the sandbox: with dryRun to see the decision without paying, with approvalId to complete a payment that was held and then approved. The endpoints are https://weather.sandbox.spendctl.dev/weather?city=<name> ($0.01) and https://search.sandbox.spendctl.dev/search?q=<query> ($0.02), as listed by sandbox_create and documented at https://spendctl.dev/docs/sandbox/; any other host is refused. Returns a one-line summary (HTTP status, amount paid, decision, receipt id) followed by the response body, or the refusal with its reason, or an approval id when the payment is waiting for a human. Only sandbox hosts exist and no real funds are involved; the request is always a GET and responses are clipped at 20,000 characters. Example: url https://weather.sandbox.spendctl.dev/weather?city=Kyoto
approve
approve
Approves or denies a payment that sandbox_pay reported as waiting for approval, as the human approver would with `spendctl approve`. Use it only with an approval id from this sandbox; in the real product a human decides, in the sandbox the model plays that role. Returns the approval id and its new status (approved or denied). An approved payment completes when sandbox_pay is called again with the same approvalId; a denied one stays refused. Deciding the same approval twice keeps the first decision.
await
await_approval
Waits for the decision on a payment that sandbox_pay reported as held, without paying again: long-polls the sandbox sidecar for up to timeoutSeconds (default 10, at most 20) and returns pending, approved, denied, expired or withdrawn, with the ledger entry and the decision deadline. This is what an agent does in the real product while a human decides; in the sandbox the model is also the approver (approve), so call approve from another turn or first. After approved, repeat sandbox_pay with approvalId to complete the payment. Read-only; never pays and never decides.
budget
check_budget
Shows the sandbox agent's spending limits, what has been spent in each window and what is left. Use it before a paid call when the remaining budget matters, or after a refusal to see which limit was hit. Returns the agent name and mode, the per-request limit, the approval threshold, what happens when a budget is exceeded, the allowed hosts and one line per window (hourly, daily: spent, limit, remaining). Read-only; changes nothing.
policy
get_policy
Returns the sandbox's spendctl.yaml as text: the preset name and the agent's budgets, allowed hosts and approval rules. Use it to explain why a payment was refused or held, or to show what a spendctl policy file looks like. Read-only; the sandbox policy cannot be changed, create a sandbox with another preset instead.
receipts
list_receipts
Lists the sandbox agent's most recent payment attempts, newest first: paid (amount and mock transaction hash), refused (reason codes) and waiting for approval. Use it to report what happened so far or to find a receipt id; after a hold, the approval id is in the sandbox_pay result. Returns up to `limit` lines, one per attempt, with time, receipt id, method, URL, amount and status, or "No payments yet." Read-only.
withdraw
withdraw_approval
Takes back a payment that sandbox_pay reported as held, as a real agent does when the task that needed the payment was cancelled or superseded: nothing is paid, the approval closes as withdrawn (distinct from deny), a later approve on that id is refused and await_approval answers withdrawn at once. Use it with an approval id from this sandbox; a new sandbox_pay call opens a fresh approval if the payment is wanted after all. Withdrawing an id that was already decided reports that decision as an error.

Endpoints

URLTransportStateLatencyChecked
https://mcp.spendctl.dev/mcp streamable-http answering 391 ms 1 min ago

Alternatives to spendctl

same job, measured the same way
Rein
by bugiiiii11

Spend limits for AI agents that pay with x402: every paywall is policy-checked before a cent moves.

94 installs/wk local only
AgentTrust XRPL
by eamwhite1

Escrow for AI agents on the XRP Ledger. 51 tools. Free testnet sandbox (no real XRP).

51 tools answering
Presidio Hardened X402 MCP
by presidio-v

Pre-payment safety gate for x402 agents: PII screening, spend policy, replay checks before signing.

553 installs/wk local only
Janus Pay
by sirbiscuits1

Janus Pay for agents: take payments that settle in BSV, refund them, and pay x402 paywalls.

829 installs/wk local only
ClawPay MCP — Non-Custodial x402 Payments for AI Agents
by up2itnow0822

Non-custodial x402 payments for AI agents. Sign locally, spend limits, Base network.

77 installs/wk local only
Agent Spend Policy MCP
by dingdawg

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

50 installs/wk local only
P0: sanctions, KYB and payee checks
by workers-x402-bazaar-rank-worker-x402-bazaar-rank

Sanctions screening, LEI lookup and payee checks for AI agents, pay per call over x402 or MPP

11 tools answering
T
Tabula MCP
by tabulacredit

Credit for AI agents: pay x402 sellers from a credit line, repay with one signature and no ETH

local only

spendctl — questions

Answers built from our own checks of this server.

What can spendctl do?
It exposes 8 tools, read directly from the server on our last check. Among them: approve, await_approval, check_budget, get_policy, list_receipts, sandbox_create and 2 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is spendctl working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 301 ms. The bar chart above shows every period we have measured.
How do I connect spendctl?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does spendctl need an API key?
No. spendctl completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 8 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is spendctl?
It answers our handshake in 301 ms on average, which is faster than 46% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.