mcpbeat Sign in

Run Budget Guard MCP Server

by botrecipe Your server? Claim it
answering

Run Budget Guard is answering right now. Last checked 3 min ago. It exposes 6 tools.

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

Uptime history 22 hours of history
22 hours agonow
100.0%
Uptime 24h
80 of 80 checks
6
Tools
read from the server
267 ms
Response time
average over 24h
open, no key
Access
streamable-http

Nothing serious here today

Today is the operative word: we check Run Budget Guard 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 3 min ago.

run in your terminal
claude mcp add budget --transport http https://budget.cloudforbots.com/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "budget": {
      "url": "https://budget.cloudforbots.com/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.budget]
url = "https://budget.cloudforbots.com/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "budget": {
      "url": "https://budget.cloudforbots.com/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "budget": {
      "url": "https://budget.cloudforbots.com/mcp"
    }
  }
}

Available tools 6

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

budget
budget_status
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.
open
open_budget
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.
record
record
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.
reserve
reserve
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.
usage
usage_and_upgrade
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.
weekly
weekly_report
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.

Endpoints

URLTransportStateLatencyChecked
https://budget.cloudforbots.com/mcp streamable-http answering 342 ms 3 min ago

Alternatives to Run Budget Guard

same job, measured the same way
Holon
by useholon

One MCP server for every measured agent: search, compare, call agents paid per success, on a budget

answering
Handoff — publish agent results as shareable pages
by workers-notdown-app-handoff

Give your agent one stable URL to publish a result or keep a page updated every run. One call.

7 tools answering
Basicdeploy MCP
by akacianl

The runtime your agent deploys to — DB, storage, and a public URL in one MCP call.

51 installs/wk local only
ljos
by leidarljos

Local memory, a work tracker and a shell-command guard shared by coding agents on one machine.

local only
AgentRaaS wrap
by sumedhchatse

Wraps any MCP server: identical write-tool calls run once, and every tool call is audit-logged.

1 091 installs/wk local only
JevSim
by huaaudio

Run verified iOS and Android UI workflows in one agent tool call with Jev.

39 installs/wk local only
Agent Observability
by kryptosai

Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.

38 installs/wk local only
4q Tokenz
by steveweltman

Intelligent MCP proxy that reduces token usage by exposing only mcp_search and mcp_call.

50 installs/wk local only

Run Budget Guard — questions

Answers built from our own checks of this server.

What can Run Budget Guard do?
It exposes 6 tools, read directly from the server on our last check. Among them: budget_status, open_budget, record, reserve, usage_and_upgrade, weekly_report. 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 Run Budget Guard working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 80 of 80 checks got a reply (100.0%), average response time 267 ms. The bar chart above shows every period we have measured.
How do I connect Run Budget Guard?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Run Budget Guard need an API key?
No. Run Budget Guard completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 6 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Run Budget Guard?
It answers our handshake in 267 ms on average, which is faster than 49% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.