Budget Governor
Budget Governor gives autonomous AI agents a hard spend limit. One budget_clear call before each LLM request checks the agent's envelope and deducts the estimated cost. Stops runaway billing before it starts. No self-hosting required.
README
Budget Governor
Hard cap on estimated AI agent spend. One MCP call before each LLM request — approved or denied before the call reaches any provider.
No deployment. No proxy. No self-hosting.
The problem
Agents cost 10–12x more than estimated in production. System prompts, retry loops, and tool calls multiply fast. A runaway agent can generate a $47,000 bill in 11 days. The common fix — self-hosting LiteLLM — requires running infrastructure most developers won't set up.
Budget Governor is the hosted alternative: an external authority your agent checks before spending.
How it works
- Your agent calls
budget_clear(MCP tool or REST) before each LLM request - The governor checks your account credit balance and the agent's spend envelope
- It returns
{ approved: true }or{ approved: false, reason: "..." } - If denied, your agent skips the call
The envelope is configured by you (per-agent daily or session cap). The credit balance is topped up via USDC on Base.
Quick start
1. Provision an account
curl -X POST https://gvnr.dev/v1/account
# { "api_key": "bg_...", "account_id": "..." }
2. Top up credits
Open the payment page for your chosen pack, pass your API key as a query param:
https://gvnr.dev/pay/starter?api_key=bg_YOUR_KEY
Send USDC on Base to the address shown, paste your tx hash — credits are added after on-chain verification.
Or, if you prefer the programmatic path — POST the tx hash directly:
curl -X POST \
-H "Authorization: Bearer bg_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"tx_hash":"0x..."}' \
https://gvnr.dev/v1/account/topup-verify/starter
3. Set an envelope for your agent
curl -X PUT \
-H "Authorization: Bearer bg_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"agent_id":"my-agent","limit_usd":5,"window":"daily"}' \
https://gvnr.dev/v1/budget/envelope
# { "success": true, "agent_id": "my-agent", "limit_usd": 5, "window": "daily" }
4. Call budget_clear before each LLM request
curl -X POST \
-H "Authorization: Bearer bg_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"agent_id":"my-agent","model":"claude-sonnet-4-6","estimated_tokens":2000}' \
https://gvnr.dev/v1/budget/clear
# { "approved": true, "remaining_usd": 4.994 }
MCP setup
Add to Claude Desktop or any MCP-compatible client:
https://gvnr.dev/mcp?api_key=bg_YOUR_KEY
Claude Code
claude mcp add budget-governor --transport http \
"https://gvnr.dev/mcp?api_key=bg_YOUR_KEY"
MCP tools
| Tool | Description |
|---|---|
budget_clear(agent_id, model, estimated_tokens) |
Check clearance and deduct estimated cost |
set_envelope(agent_id, limit_usd, window?) |
Create or update an agent's spend envelope |
get_balance() |
Get current account credit balance |
REST API
All endpoints (except POST /v1/account) require Authorization: Bearer bg_YOUR_KEY.
Account
| Method | Path | Description |
|---|---|---|
POST |
/v1/account |
Provision account — returns api_key |
GET |
/v1/account/balance |
Current credit balance |
GET |
/v1/packs/:pack/info |
Public — pack details, USDC address, raw amount |
POST |
/v1/account/topup-verify/:pack |
Submit tx hash → verify on-chain → credit account |
POST |
/v1/account/topup/:pack |
x402-gated credit top-up (machine clients) |
Budget
| Method | Path | Description |
|---|---|---|
POST |
/v1/budget/clear |
Clearance call — approve or deny |
PUT |
/v1/budget/envelope |
Create or update agent envelope |
GET |
/v1/budget/envelope/:agent_id |
Read envelope state |
Clearance response
{ "approved": true, "remaining_usd": 4.994 }
{ "approved": false, "remaining_usd": 0, "reason": "envelope_exceeded" }
Denial reasons: no_credits · no_envelope · envelope_exceeded
Credit packs
Top up at GET /pay/:pack?api_key=bg_YOUR_KEY. Send USDC on Base mainnet — credits added after on-chain verification.
| Pack | Price | Clearances | Link |
|---|---|---|---|
starter |
$19 | ~10k/month | /pay/starter |
growth |
$39 | ~30k/month | /pay/growth |
studio |
$79 | ~100k/month | /pay/studio |
Envelope windows
daily— resets at UTC midnight each daysession— never resets (use for one-shot tasks)
Supported models
Model pricing is a static lookup on the hot path — no external calls. Includes claude-opus-4-7, claude-sonnet-4-6, claude-haiku-4-5, gpt-4o, gpt-4o-mini, and others. Unknown models fall back to a conservative default.
Network
X402_NETWORK |
Chain | Notes |
|---|---|---|
eip155:84532 |
Base Sepolia | Testnet — safe for development |
eip155:8453 |
Base mainnet | Real USDC |
Current deployment: Base mainnet.
License
MIT — see LICENSE.
The canonical hosted service is at https://gvnr.dev. Self-hosted instances are unaffiliated.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。