Robot Resources Router
LLM routing proxy that cuts API costs 60-90% by auto-selecting the cheapest capable model across OpenAI, Anthropic, and Google. Provides stats, config, and model comparison tools via MCP.
README
@robot-resources/router-mcp
MCP server for managing Robot Resources Router — stats, config, and model comparison.
What is Robot Resources?
Human Resources, but for your AI agents.
Robot Resources cuts your LLM API costs by 60-90%. It runs a local proxy that classifies each prompt by task type (coding, reasoning, analysis, simple Q&A, creative, general) and routes it to the cheapest model that can handle it — across 14 models from OpenAI, Anthropic, and Google.
Your API keys never leave your machine. Free, unlimited, no tiers.
Install the full suite
npx robot-resources
One command sets up the Router proxy, configures your agents, and gets you saving immediately.
Learn more at robotresources.ai
About this MCP server
This package gives AI agents management tools for the Router proxy via the Model Context Protocol. Use it to check cost savings, compare models, and adjust routing config — all from within Claude Desktop, Claude Code, or any MCP-compatible agent.
Quick Start
npx @robot-resources/router-mcp
Requires the Router proxy running at localhost:3838 (default). Override with ROUTER_URL env var.
Configuration
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"router": {
"command": "npx",
"args": ["-y", "@robot-resources/router-mcp"]
}
}
}
Claude Code
Add to your .mcp.json:
{
"mcpServers": {
"router": {
"command": "npx",
"args": ["-y", "@robot-resources/router-mcp"]
}
}
}
Custom Router URL
If the proxy runs on a non-default port:
{
"mcpServers": {
"router": {
"command": "npx",
"args": ["-y", "@robot-resources/router-mcp"],
"env": {
"ROUTER_URL": "http://localhost:4000"
}
}
}
}
Tools
router_get_stats
Cost savings statistics for the Router proxy.
| Parameter | Type | Default | Description |
|---|---|---|---|
period |
"daily" | "weekly" | "monthly" |
"weekly" |
Time period |
task_type |
string |
— | Filter by task type |
provider |
string |
— | Filter by provider |
router_compare_models
Compare models by capability and cost for a given task type.
| Parameter | Type | Default | Description |
|---|---|---|---|
task_type |
string |
required | Task type to compare |
threshold |
number |
0.7 |
Minimum capability score |
provider |
string |
— | Filter by provider |
router_get_config
Read current routing configuration (provider scope, thresholds, overrides).
No parameters required.
router_set_config
Update routing configuration at runtime. Changes are in-memory only (reset on restart).
| Parameter | Type | Description |
|---|---|---|
provider_scope |
string |
Limit to specific provider(s) |
capability_threshold |
number |
Minimum capability score |
baseline_model |
string |
Model for cost comparisons |
log_level |
string |
Logging level |
Pass null for any field to reset it to the env-var default.
Requirements
- Node.js >= 18.0.0
- Router proxy running (see @robot-resources/router)
License
MIT
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。