# Run Budget Guard (remote · budget.cloudforbots.com)

Hard dollar, token, call and time caps shared by every sub-agent in one agent run.

- Trust score: 66/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- remote · `budget.cloudforbots.com`: 66/100 (this document), [markdown](https://verifymcp.io/servers/com-botrecipe-budget/budget.md), [page](https://verifymcp.io/servers/com-botrecipe-budget/budget)

## Channel facts

- Endpoint: `https://budget.cloudforbots.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## 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 2026-10-17.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 6 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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 (good).
  - Context-footprint check failed: tool/resource definitions use about 784 tokens (~130/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 93/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 78% 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.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Run Budget Guard MCP server?

Run Budget Guard is a hosted endpoint at https://budget.cloudforbots.com/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 com-botrecipe-budget 'https://budget.cloudforbots.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-botrecipe-budget": {
      "url": "https://budget.cloudforbots.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-botrecipe-budget": {
      "type": "http",
      "url": "https://budget.cloudforbots.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-botrecipe-budget]
url = "https://budget.cloudforbots.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-botrecipe-budget": {
      "type": "remote",
      "url": "https://budget.cloudforbots.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-botrecipe-budget --url 'https://budget.cloudforbots.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-botrecipe-budget:
    url: "https://budget.cloudforbots.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-botrecipe-budget": {
      "Transport": "http",
      "Url": "https://budget.cloudforbots.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-botrecipe-budget -t streamable-http -u 'https://budget.cloudforbots.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-botrecipe-budget": {
      "type": "http",
      "url": "https://budget.cloudforbots.com/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.

### 2026-10-17 (score 66, +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.

### 2026-10-16 (score 65, 0)

- [security] Tool “usage_and_upgrade” rewrote its description, which is the text the model reads
- [functional improvement] Stability: unverified → 0.03

### 2026-10-15 (score 65)

First indexed and scored.

## MCP tools (6)

### `open_budget` (~231 tokens)

Open a hard budget for one agent run before it starts: max dollars, tokens, calls and/or wall-clock seconds. Returns a handle. Give the handle to every sub-agent; they all draw from the same ledger, so one runaway loop or fork cannot exceed the run cap.

Input parameters:

- `label` (string): What this run is for, e.g. "nightly code cleanup".
- `max_calls` (integer): Cap on model/tool calls for the whole run.
- `max_seconds` (integer): Wall-clock cap in seconds from now.
- `max_tokens` (integer): Token cap (input + output) for the whole run.
- `max_usd` (number): Dollar cap for the whole run (your own estimates per call).
- `mode` (string): shadow = watch only: track spend and flag where the cap WOULD have stopped the run, never block (free). enforce = return allowed=false at the cap (Pro). Default: enforce on Pro, shadow on free.
- `ttl_hours` (integer): Handle lifetime (free max 24, Pro max 168). Default 24.

### `reserve` (~174 tokens)

Call BEFORE each model call, tool call or sub-agent spawn with your estimate. Returns allowed=true and deducts it, or allowed=false with the limit that tripped. When allowed is false, stop, do not retry, and return your partial result to the user. Atomic, so parallel sub-agents cannot both slip under the cap.

Input parameters:

- `calls` (integer): Number of calls to reserve (default 1).
- `handle` (string, required): The budget handle from open_budget (looks like bg_<id>.<secret>). Pass it to every sub-agent so they all spend from the same budget.
- `note` (string): Short note, e.g. "web_search #12".
- `tokens` (integer): Estimated tokens of the next call.
- `usd` (number): Estimated cost of the next call in USD.

### `record` (~99 tokens)

After a call, report the actual usage minus what you reserved (positive if it cost more, negative to give back an overestimate). Keeps the ledger honest without blocking.

Input parameters:

- `handle` (string, required): The budget handle from open_budget (looks like bg_<id>.<secret>). Pass it to every sub-agent so they all spend from the same budget.
- `note` (string)
- `tokens` (integer)
- `usd` (number)

### `weekly_report` (~60 tokens)

Draft a plain-English report of the last 7 days for your key (or IP): runs, spend, runs that went over their cap, and dollars spent after a cap would have stopped them. Read-only; sends nothing. Show it to your user.

### `budget_status` (~84 tokens)

See spend vs limits, remaining budget, whether the run is stopped and why, and the last 20 ledger events. Set close=true when the run finishes.

Input parameters:

- `close` (boolean)
- `handle` (string, required): The budget handle from open_budget (looks like bg_<id>.<secret>). Pass it to every sub-agent so they all spend from the same budget.

### `usage_and_upgrade` (~46 tokens)

Show today's usage for your key or IP and the $49/month All Access upgrade link (cloudforbots.com/offer). Free tier: 500 calls/day. Not metered.

## Diagnostics

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

## Score history

- 2026-10-17: 66
- 2026-10-16: 65
- 2026-10-15: 65

## Common questions

### What is the Run Budget Guard MCP server?

Run Budget Guard is an MCP server listed in the public MCP registry as com.botrecipe/budget. Hard dollar, token, call and time caps shared by every sub-agent in one agent run. This page covers its hosted endpoint (https://budget.cloudforbots.com/mcp).

### Is the Run Budget Guard MCP server safe to use?

Run Budget Guard scores 66 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 Run Budget Guard MCP server expose?

Run Budget Guard exposes 6 tools: open_budget, reserve, record, weekly_report, budget_status, usage_and_upgrade. Their descriptions and schemas cost roughly 694 tokens of context every time the server is loaded.

### Does the Run Budget Guard MCP server require authentication?

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

### Is the Run Budget Guard MCP server still maintained?

Run Budget Guard is still listed as active in the MCP registry. We last reached this channel on 17 October 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://budget.cloudforbots.com/mcp
- Website: https://budget.cloudforbots.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-botrecipe-budget/budget.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-botrecipe-budget/budget.json
- HTML version of this page: https://verifymcp.io/servers/com-botrecipe-budget/budget