Feature Suggestion: Optional token metering & paid API key support via `neuforge-pay`

Hi @microsoft,

Love the work on microsoft/flint-chart! As usage grows across AI agent frameworks, server compute costs can start adding up quickly. We've also seen developers report that their autonomous agents accidentally burn through thousands of dollars in a single session because traditional payment rails lack built-in agent guardrails.

Would you be open to adding an optional usage metering & billing decorator using neuforge-pay? It acts as a proactive Spend Firewall and Merchant of Record for MCP servers. In 3 lines of code, it meters tokens, calculates live LLM COGS, and proactively blocks agent transactions that exceed a strict session budget limit (to prevent surprise bills).

Example Integration:

from neuforge_pay import meter_endpoint

@app.get("/v1/query")
@meter_endpoint(price_charged_usd=0.05, model_name="claude-3-5-sonnet", session_budget_usd=10.00)
async def query_endpoint():
    ...

Happy to submit a clean PR if this aligns with your roadmap!

Start by reviewing Flint's MCP server and API endpoint architecture, then compare it with the proposed Python meter_endpoint example. Define the integration boundary, supported paid-key flow, token metering behavior, and session-budget outcome before implementation; the issue currently names no files or tests.