Argus API Spend
Track API spend, credit balances and runway across OpenAI, Anthropic, OpenRouter and 25 more.
我该使用它吗
质量与安全性
发现（7）
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains URL to non-standard domain在 list_available_providers 中
- LOWTool 'get_overview' description lacks action verb在 get_overview 中
- LOWTool 'get_provider' description lacks action verb在 get_provider 中
- LOWTool 'get_advisories' description lacks action verb在 get_advisories 中
- LOWTool 'get_cost_accuracy' description lacks action verb在 get_cost_accuracy 中
- LOWTool 'sync_connection' description lacks action verb在 sync_connection 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"argus": {
"url": "https://api.argus.town/mcp"
}
}
}远程端点
https://api.argus.town/mcpstreamable-http它能做什么
工具清单
工具（10）
🟢list_connections
List the org's connected providers and status.
输入模式
{
"type": "object",
"properties": {}
}🟢get_overview
Cross-provider rollup: balance, burn rate, days-to-zero, month-to-date spend, projection, rate-limit headroom.
输入模式
{
"type": "object",
"properties": {}
}🟢get_provider(connectionId)
Full metrics + rate-limit snapshots for one connection id.
输入模式
{
"type": "object",
"properties": {
"connectionId": {
"type": "string"
}
},
"required": [
"connectionId"
]
}🟢get_rate_limit_status
Latest rate-limit headroom and error rate across the org's providers.
输入模式
{
"type": "object",
"properties": {}
}🟢get_advisories
All current advisories (top-up, upgrade, near-limit, spend-spike) across providers.
输入模式
{
"type": "object",
"properties": {}
}🟢get_cost_accuracy
Cost-accuracy state per provider: whether itemized costs are exact, estimated, or unreconciled, with the drift % between Argus's itemized total and the provider's own reported spend.
输入模式
{
"type": "object",
"properties": {}
}🟢get_request_costs(provider, limit)
Recent itemized per-request costs for a provider (model, tokens, cost in USD, provenance). Args: provider (string), limit (number, default 25, max 100).
输入模式
{
"type": "object",
"properties": {
"provider": {
"type": "string",
"description": "Provider id, e.g. 'openrouter'"
},
"limit": {
"type": "number"
}
},
"required": [
"provider"
]
}🟢list_available_providers
Providers that can be connected with an API key (poll plane). Anything else can still be tracked by sending telemetry — see https://argus.town/docs/ingest.
输入模式
{
"type": "object",
"properties": {}
}🟢connect_provider(provider, secret, credential_type, label)
Connect a provider to THIS project with a credential. Validates the credential against the provider before storing it (encrypted), then queues the initial sync. Args: provider (id from list_available_providers), secret (the provider API key), credential_type (optional), label (optional). Only pass secrets your operator gave you for this purpose.
输入模式
{
"type": "object",
"properties": {
"provider": {
"type": "string"
},
"secret": {
"type": "string"
},
"credential_type": {
"type": "string"
},
"label": {
"type": "string"
}
},
"required": [
"provider",
"secret"
]
}⚪sync_connection(connection_id)
Queue an immediate balance/usage/plan refresh for one connection. Args: connection_id.
输入模式
{
"type": "object",
"properties": {
"connection_id": {
"type": "string"
}
},
"required": [
"connection_id"
]
}社区
证据