Budgetary: estimate token spend
Pre-flight token-spend estimate (range, scenario, confidence) for a coding task, or an abstention.
Open the source (opens github.com) https://github.com/thriftell/budgetary-clients
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
- Needs credentials: BUDGETARY_API_KEY. Use a key with the least access you can.
What it is
MCP servers from io.github.thriftell.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
npm package (stdio)
@budgetary/mcp@0.13.0
From the server's entry in the official MCP Registry
Settings it asks for
BUDGETARY_API_KEYsecret required · Budgetary API key (bg_live_ or bg_test_ prefix). Get one at https://budgetary.tools.BUDGETARY_HOST· Optional tag naming the MCP host this server runs under — e.g. claude-code, cursor, codex, copilot. It labels each estimate with where it came from, and an…
Related
-
Accent site content
MCP serversSearch Accent's public website and get non-binding budgetary estimates from published plan prices.
-
Whitespace token estimate, text discarded
MCP serversWhitespace token estimate, text discarded
-
llm-cost-estimator
MCP serversToken counting & multi-model LLM cost estimates: GPT-4o, Claude, Gemini, 25+. No API key.
llm-cost-estimator-mcp@0.3.1 -
tokencast
MCP serversPre-execution cost estimation for LLM agent workflows with calibration learning
tokencast@0.1.1 -
tokencost-dev
MCP serversLLM pricing oracle — model lookup, cost estimation, and comparison via LiteLLM
tokencost-dev@0.1.3 -
TokenOracle
MCP serversHosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
token-oracle-mcp@1.0.1