Budgetary: estimate token spend is answering right now. Last checked 10 min ago. 79 installs a week from npm. It exposes 1 tools. Last commit 18 Aug 2026.
Pre-flight token-spend estimate (range, scenario, confidence) for a coding task, or an abstention.
Today is the operative word: we check Budgetary: estimate token spend every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.
claude mcp add budgetary --transport http https://api.budgetary.tools/mcp
https://api.budgetary.tools/mcp
[mcp_servers.budgetary]
url = "https://api.budgetary.tools/mcp"
{
"mcpServers": {
"budgetary": {
"url": "https://api.budgetary.tools/mcp"
}
}
}
{
"servers": {
"budgetary": {
"type": "http",
"url": "https://api.budgetary.tools/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
estimate
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.budgetary.tools/mcp | streamable-http | answering | 394 ms | 10 min ago |
Pre-flight spend authorization for AI agents. Set a budget, enforce limits, audit every decision.
Token budget auditor for agent context: per-file estimates, top offenders, exclusion advice.
Search Accent's public website and get non-binding budgetary estimates from published plan prices.
A hard budget cap for Cloudflare Workers: see estimated spend and pause or resume Workers.
Token and context budget for AI agents. Tracks spend and gates the session.
Persistent, evidence-backed project knowledge and task context for coding agents.
Count tokens (o200k/cl100k), truncate to a budget, chunk text for RAG and estimate LLM cost.
Token efficient search for coding agents over public and private documentation.
Answers built from our own checks of this server.