Agent Token Budget Mcp
Cap how much each agent session can spend on tokens and get a signed record when the budget is hit.
Overview
Agent Token Budget MCP is an Operate-phase MCP server that enforces per-session token spend caps and returns signed attestations when a budget is exhausted.
What is this MCP server?
- Per-session token spend cap enforced by the MCP server
- Signed budget-exhausted attestations for audit and downstream gates
- stdio transport via PyPI package agent-token-budget-mcp v1.1.1
- Pairs conceptually with broader budget/fleet tooling (twin of bf)
- Runs as a local MCP process for Claude Code, Cursor, and similar hosts
- MCP server version 1.1.1
- 1 PyPI package with stdio transport
- Registry identifier: agent-token-budget-mcp
What problem does it solve?
Agent sessions can burn through API tokens with no per-run limit, leaving solo builders with surprise bills and no proof of when spending was intentionally stopped.
Who is it for?
Solo builders running Claude Code or Cursor agents against paid APIs who want session-level spend caps and attestations without a full billing stack.
Skip if: Teams that only need monthly invoices from OpenAI or Anthropic with no per-session enforcement or signed stop events.
What do I get? / Deliverables
Each session runs under a defined token budget, and when it hits the cap you get signed budget-exhausted attestations you can audit or chain into other tools.
- Enforced per-session token spend ceiling during agent runs
- Signed budget-exhausted attestations when a session hits its cap
- stdio MCP integration listed as agent-token-budget-mcp v1.1.1
Recommended MCP Servers
Journey fit
Token spend control is an ongoing production concern once agents are running against live models, not a one-time build task. Monitoring fits spend tracking and enforced limits per session with attestations when limits are reached.
How it compares
MCP spend-guard integration, not an LLM skill or provider billing portal.
Common Questions / FAQ
Who is agent-token-budget-mcp for?
It is for indie and solo builders who run coding agents on metered LLM APIs and need per-session caps plus signed proof when a budget runs out.
When should I use agent-token-budget-mcp?
Use it in production or heavy local agent workflows once token cost becomes a risk—before unattended loops, demos, or customer-facing agent features go live.
How do I add agent-token-budget-mcp to my agent?
Install the PyPI package agent-token-budget-mcp, add it as a stdio MCP server in Claude Code, Cursor, or another MCP host, and configure per-session budget settings in that host’s MCP config.