How to choose
What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the LLM Usage MCP server?
Local-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via MCP
How to install LLM Usage
Copy-paste configuration for popular MCP clients.
transport: stdio
Config generated by PluginBench — verify against the source before use.~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
"mcpServers": {
"llm-usage-mcp": {
"command": "uvx",
"args": [
"llm-usage-mcp"
]
}
}
}Related MCP servers
CH

Chenji Affect
Active
Affect analysis, 3D avatar params, empathy hints and somatic emotion decode.
0
View repository →Python
MIT
IO

AI-powered image generation with Google Gemini models—Flash speed meets 4K quality
392
View repository →Python
MIT
IO

Local-first Sui DeFi evidence and review for AI clients before wallet signing.
0
View repository →TypeScript
MIT
IF

iFlow Search
Maintained
Web search, image search, and URL fetch via iFlow Search API with AI-friendly structured output.
31
View repository →TypeScript
MIT
AI

知你AI助手|多平台客户与客服数据 MCP
Active
连接个微、企微、视频号、微信小程序、公众号、服务号、微信客服、微信小店、抖音号、小红书、微博、网站及H5客服的客户资料、会话与聊天记录,供AI查询分析。
0
View repository →