spendctl
Server Details
Spend policy for AI agents that pay (x402, MPP). Login-free sandbox, real sidecar, no real funds.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 8 tools
Each tool targets a distinct action in the sandbox payment lifecycle, and the descriptions explicitly cross-reference the easily confused trio (approve decides, await_approval only waits/reads, withdraw_approval cancels). sandbox_pay, sandbox_create, check_budget, get_policy and list_receipts are all clearly separated by resource and intent.
All names are snake_case and verb-first, which is predictable. The only deviation is the sandbox_ prefix group (sandbox_create, sandbox_pay) versus bare verbs elsewhere (approve, list_receipts, get_policy), plus the bare 'approve' lacking a noun.
Eight tools is well within a healthy range and every tool earns its place: sandbox setup, one payment path, budget/policy introspection, receipts, and the three approval-state operations. Nothing feels padded or missing for redundancy.
The paid-call lifecycle is fully covered: create sandbox, inspect budget/policy, pay (with dryRun and approvalId), hold, approve/deny, withdraw, await decision, and review receipts. Minor gaps exist around sandbox lifecycle management (no list/describe/delete sandbox, only implicit expiry) and no direct way to enumerate pending approvals aside from an approval id returned by sandbox_pay.
Available Tools
8 toolsapproveApprove or deny a held sandbox paymentAIdempotentInspect
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.
Inputs: approvalId (required), sandbox_id (required), note, decision.
await_approvalWait for a held sandbox payment's decisionARead-onlyInspect
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the sandbox sidecar for up to timeoutSeconds (default 10, at most 20) and returns pending, approved, denied, expired or withdrawn, with the ledger entry and the decision deadline.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.
Inputs: approvalId (required), sandbox_id (required), timeoutSeconds.
check_budgetCheck remaining budgetARead-onlyInspect
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.
Inputs: sandbox_id (required).
get_policyShow the sandbox policyARead-onlyInspect
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.
Inputs: sandbox_id (required).
list_receiptsList receiptsARead-onlyInspect
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.
Inputs: sandbox_id (required), limit.
sandbox_createCreate a spendctl sandboxAInspect
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.
Inputs: preset.
sandbox_payFetch a paid sandbox URLAInspect
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= ($0.01) and https://search.sandbox.spendctl.dev/search?q= ($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. On a client that supports MCP input requests (protocol revision 2026-07-28, form elicitation) a held payment comes back as an input_required result asking the user to approve or deny, and the client's retry completes or refuses it; other clients get the approval id as text. 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
Inputs: url (required), sandbox_id (required), dryRun, approvalId, +1 more.
withdraw_approvalWithdraw a held sandbox paymentAIdempotentInspect
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.
Inputs: approvalId (required), sandbox_id (required), note.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Advisory policy preflight for AI-agent spend requests; never executes payments or accesses wallets.
Policy-gated MCP treasury for AI agents — x402 subscribe, 50+ tools, multi-chain.
Safety checks for AI agents paying on Base: free SpendGuard, paid x402 token risk and preflight.
Public demo: evaluate AI-agent payment authorization and approval policy. No signing, no settlement.
Related MCP Servers
- AlicenseBqualityBmaintenanceEnables AI agents to make policy-scoped payments with spending caps, recipient allowlists, approval thresholds, instant revocation, and an append-only audit trail in a sandbox wallet.10MIT
- AlicenseAqualityBmaintenanceSpend limits for AI agents that pay with x402: every paywall is policy-checked before a cent moves.58 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to pay x402 endpoints on Cardano through a policy-gated wallet with spend caps, payee allowlists, human approval, and an audit log.215 npmApache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to request policy-governed payments through MCP tools, with server-side enforcement of spending limits, merchant allow-lists, Pix BR Code validation, approval thresholds, and hash-chained audit logging in a sandbox. It lets agents check wallets, create card or Pix payment intents, and poll or list payments while keeping approval and limit changes out of agent control.Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.