A proxy tool for composing multiple MCP servers into one unified endpoint. Scale your AI tools by load balancing requests across multiple MCP servers, similar to how Nginx works for web servers.
Run the underlying MCP server directly — without Agent-CoreX routing.
npx -y mcgravityAgent-CoreX intelligently routes which tools from tigranbs/mcgravity your AI agent actually needs per request — reducing token usage and cost.
agent-corex.json
{
"mcpServers": {
"mcgravity": {
"command": "npx",
"args": [
"-y",
"mcgravity"
]
}
}
}Connect in 2 minutes. Only pay for the tools your agent actually uses.
A collection of reference implementations for the Model Context Protocol (MCP), showcasing its features and SDK usage.
A CLI inspector for the Model Context Protocol that allows running MCP servers and interacting with various tools and resources.
A project related to the Model Context Protocol, potentially involving data processing or context management.
Recommended: intelligent tool routing, lower costs
uvx agent-corex mcp add mcgravityAgent-CoreX selects only the tools your agent needs, cutting token usage by up to 60%.
Use tigranbs/mcgravity directly without routing
npx -y mcgravityNew to Agent-CoreX? View setup guide →