Meta MCP Proxy
Meta MCP 代理
一个灵活的模型上下文协议 (MCP) 代理,支持跨多个 MCP 服务器和 JavaScript 函数发现和执行工具。如果您拥有大量工具,则可以减少上下文事件。此 MCP 充当其他 MCP(或库)的包装器,执行某种本地 RAG(检索增强生成)操作以缩减上下文大小,为 LLM 提供两种方法(发现和执行),并要求 LLM 简洁地进行发现。执行方法是一个简单的代理
我们极力建议添加配置discoverDescriptionExtras来扩展有关工具用途的详细信息以及 llm 应该将其用于哪些类型的主题。
特征
🌉统一工具发现:跨多个 MCP 服务器搜索工具
🔌代理执行:将工具调用路由到适当的服务器
🔍智能搜索:通过模糊匹配找到最适合工作的工具
🧩 JavaScript 集成:将自定义 JavaScript 函数公开为 MCP 工具
📝可配置:从文件或命令行参数加载配置
Related MCP server: mcptool
用法
🧱 安装
编辑文件~/Library/Application Support/Claude/claude_desktop_config.json
并添加以下内容
{
"mcpServers": {
"mcp-openapi-proxy": {
"command": "npx",
"args": ["@nullplatform/meta-mcp-proxy","-f","config.json"]
}
}
}配置文件格式
您的config.json应该遵循以下结构:
{
"discoverDescriptionExtras": "Additional description for discovery",
"discoverLimit": 10,
"mcpServers": {
"server-name": {
"command": "command-to-execute",
"args": ["arg1", "arg2"],
"env": {
"ENV_VAR1": "value1",
"ENV_VAR2": "value2"
},
"transport": "stdio"
}
}
}例如
{
"discoverDescriptionExtras": "Api used to manage a pet store with access to pets, pet types, users, orders and store",
"mcpServers": {
"mcp-petstore": {
"command": "uvx",
"args": ["mcp-openapi-proxy"],
"env": {
"OPENAPI_SPEC_URL": "https://petstore.swagger.io/v2/swagger.json",
"API_KEY": "xxxxx"
}
}
}
}与 Claude 的 0-Shot 对话示例
该示例使用宠物商店的演示配置,几乎没有对 API 的描述

作为图书馆
您还可以在自己的 JavaScript 应用程序中将 Meta MCP Proxy 用作库:
import { MCPProxy } from '@nullplatform/meta-mcp-proxy';
// Create a new proxy instance
const mcpProxy = new MCPProxy({
mcpServers: {
"my-server": {
"command": "path/to/server",
"args": [],
"env": {}
}
},
discoverLimit: 10
});
// Register a custom JavaScript function
mcpProxy.registerJsFunction(
"myFunction",
"Description of my function",
{
properties: {
param1: {
type: "string",
description: "First parameter"
},
param2: {
type: "number",
description: "Second parameter"
}
},
required: ["param1"]
},
async ({ param1, param2 }) => {
// Implementation goes here
return {
content: [
{
type: "text",
text: JSON.stringify({ result: `Processed ${param1}` })
}
]
};
}
);
// Start the MCP server
await mcpProxy.startMCP();使用 meta-mcp-proxy 作为库创建 mcp 的示例
执照
麻省理工学院
This server cannot be deployed
Maintenance
Related MCP Connectors
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceA proxy server that wraps existing MCP servers to significantly reduce token consumption by compressing tool descriptions into a two-step interface. It enables users to integrate extensive toolsets without exceeding context limits or incurring high API costs.129Apache 2.0
- AlicenseNot gradedqualityNot gradedmaintenanceA drop-in MCP proxy that aggregates multiple backend servers into two meta-tools for efficient tool discovery and execution. It enables AI clients to access hundreds of tools while minimizing context window usage through searchable indexing.1 npm-
- AlicenseNot gradedqualityDmaintenanceMCP proxy that reduces context usage through semantic tool routing, enabling on-demand discovery and routing of relevant tools.MIT
- AlicenseAqualityCmaintenanceA smart MCP proxy server that lazily loads relevant MCP tool servers based on project context, keeping AI tool counts within recommended limits. It enables agents to dynamically activate, deactivate, and discover MCP servers to optimize context usage.133MIT