# spendctl (remote · mcp.spendctl.dev)

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

- Trust score: 70/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `mcp.spendctl.dev`: 70/100 (this document), [markdown](https://verifymcp.io/servers/dev-spendctl-spendctl/mcp.md), [page](https://verifymcp.io/servers/dev-spendctl-spendctl/mcp)

## Channel facts

- Endpoint: `https://mcp.spendctl.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1754 tokens (~219/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the spendctl MCP server?

spendctl is a hosted endpoint at https://mcp.spendctl.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http dev-spendctl-spendctl 'https://mcp.spendctl.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-spendctl-spendctl": {
      "url": "https://mcp.spendctl.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-spendctl-spendctl": {
      "type": "http",
      "url": "https://mcp.spendctl.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-spendctl-spendctl]
url = "https://mcp.spendctl.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-spendctl-spendctl": {
      "type": "remote",
      "url": "https://mcp.spendctl.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-spendctl-spendctl --url 'https://mcp.spendctl.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-spendctl-spendctl:
    url: "https://mcp.spendctl.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-spendctl-spendctl": {
      "Transport": "http",
      "Url": "https://mcp.spendctl.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-spendctl-spendctl -t streamable-http -u 'https://mcp.spendctl.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dev-spendctl-spendctl": {
      "type": "http",
      "url": "https://mcp.spendctl.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 69, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 1329 → 1754
- [functional] New tool “await_approval”
- [functional] New tool “withdraw_approval”

### 2026-11-02 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 66, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “list_receipts” rewrote its description, which is the text the model reads
- [security] Tool “approve” rewrote its description, which is the text the model reads
- [security] Tool “check_budget” rewrote its description, which is the text the model reads
- [security] Tool “get_policy” rewrote its description, which is the text the model reads
- [security] Tool “sandbox_create” rewrote its description, which is the text the model reads
- [security] Tool “sandbox_pay” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 76% → 100%
- [functional improvement] Stability: unverified → 0.03
- [functional] Schema quality: good → excellent
- [cosmetic] “approve” reworded the description of “approvalId”
- [cosmetic] “approve” reworded the description of “decision”
- [cosmetic] “approve” reworded the description of “note”
- [cosmetic] “approve” reworded the description of “sandbox_id”
- [cosmetic] “check_budget” reworded the description of “sandbox_id”
- [cosmetic] “get_policy” reworded the description of “sandbox_id”
- [cosmetic] “list_receipts” reworded the description of “limit”
- [cosmetic] “list_receipts” reworded the description of “sandbox_id”
- [cosmetic] “sandbox_create” reworded the description of “preset”
- [cosmetic] “sandbox_pay” reworded the description of “approvalId”
- [cosmetic] “sandbox_pay” reworded the description of “dryRun”
- [cosmetic] “sandbox_pay” reworded the description of “idempotencyKey”
- [cosmetic] “sandbox_pay” reworded the description of “sandbox_id”
- [cosmetic] “sandbox_pay” dropped the optional parameter “body”
- [cosmetic] “sandbox_pay” dropped the optional parameter “headers”
- [cosmetic] “sandbox_pay” dropped the optional parameter “method”

### 2026-10-26 (score 65)

First indexed and scored.

## MCP tools (8)

### `sandbox_create` (~227 tokens)

Create a spendctl sandbox

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; 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.

Input parameters:

- `preset` (string): Policy preset. default: comfortable caps, both endpoints allowed; strict: $0.015 per request and $0.03 per day, weather only, so the search API and a fourth weather call are refused; approvals: payme…

### `sandbox_pay` (~387 tokens)

Fetch a paid sandbox URL

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

Input parameters:

- `approvalId` (string): The approval id from an earlier sandbox_pay result, after approve accepted it, to complete that held payment
- `dryRun` (boolean): true: only report what spendctl would decide; never pay
- `idempotencyKey` (string): Reuse the same key when retrying a call so the sandbox is never charged twice, e.g. "kyoto-1"
- `sandbox_id` (string, required): The sandbox_id returned by sandbox_create (32 hex characters)
- `url` (string, required): Absolute URL of a sandbox endpoint, e.g. https://weather.sandbox.spendctl.dev/weather?city=Kyoto

### `await_approval` (~204 tokens)

Wait for a held sandbox payment's decision

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.

Input parameters:

- `approvalId` (string, required): The approval id returned by sandbox_pay in its "waiting for approval" result (Approval id: ...)
- `sandbox_id` (string, required): The sandbox_id returned by sandbox_create (32 hex characters)
- `timeoutSeconds` (integer): How long to wait for a decision before answering pending (1 to 20, default 10)

### `withdraw_approval` (~183 tokens)

Withdraw a held sandbox payment

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.

Input parameters:

- `approvalId` (string, required): The approval id returned by sandbox_pay in its "waiting for approval" result (Approval id: ...)
- `note` (string): Optional reason recorded with the withdrawal, e.g. "task cancelled", up to 200 characters
- `sandbox_id` (string, required): The sandbox_id returned by sandbox_create (32 hex characters)

### `check_budget` (~120 tokens)

Check remaining 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.

Input parameters:

- `sandbox_id` (string, required): The sandbox_id returned by sandbox_create (32 hex characters)

### `list_receipts` (~147 tokens)

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.

Input parameters:

- `limit` (integer): How many attempts to return, newest first (1 to 100, default 10)
- `sandbox_id` (string, required): The sandbox_id returned by sandbox_create (32 hex characters)

### `get_policy` (~94 tokens)

Show the sandbox 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.

Input parameters:

- `sandbox_id` (string, required): The sandbox_id returned by sandbox_create (32 hex characters)

### `approve` (~192 tokens)

Approve or deny a held sandbox payment

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.

Input parameters:

- `approvalId` (string, required): The approval id returned by sandbox_pay in its "waiting for approval" result (Approval id: ...)
- `decision` (string): approve releases the held payment; deny refuses it for good
- `note` (string): Optional reason recorded with the decision, up to 200 characters
- `sandbox_id` (string, required): The sandbox_id returned by sandbox_create (32 hex characters)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-spendctl-spendctl/mcp#diagnostics

## Score history

- 2026-11-05: 70
- 2026-11-04: 70
- 2026-11-03: 69
- 2026-11-02: 69
- 2026-11-01: 68
- 2026-10-31: 68
- 2026-10-30: 67
- 2026-10-29: 67
- 2026-10-28: 67
- 2026-10-27: 66
- 2026-10-26: 65

## Common questions

### What is the spendctl MCP server?

spendctl is an MCP server listed in the public MCP registry as dev.spendctl/spendctl. Spend policy for AI agents that pay (x402, MPP). Login-free sandbox, real sidecar, no real funds. This page covers its hosted endpoint (https://mcp.spendctl.dev/mcp).

### Is the spendctl MCP server safe to use?

spendctl scores 70 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the spendctl MCP server expose?

spendctl exposes 8 tools: sandbox_create, sandbox_pay, await_approval, withdraw_approval, check_budget, and 3 more. Their descriptions and schemas cost roughly 1,554 tokens of context every time the server is loaded.

### Does the spendctl MCP server require authentication?

No. We connected to spendctl without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the spendctl MCP server still maintained?

spendctl is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.spendctl.dev/mcp
- Website: https://spendctl.dev/docs/sandbox/
- Changelog RSS feed: https://verifymcp.io/servers/dev-spendctl-spendctl/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-spendctl-spendctl/mcp.json
- HTML version of this page: https://verifymcp.io/servers/dev-spendctl-spendctl/mcp