HiveCompute MCP Server is a decentralized inference router for AI agents and an OpenAI-compatible inference broker. It supports paying per token in USDC on Base L2, and is presented as part of the MCP ecosystem.
🛠️ Key Features
OpenAI-compatible inference broker
Decentralized inference router for AI agents
Pay per token in USDC on Base L2
Related to topics: hive-civilization, mcp, model-context-protocol, agent-commerce, payments, x402, settable
🚀 Use Cases
Routing AI agent inference requests through an MCP server interface
Using an OpenAI-compatible endpoint pattern for agent tooling
Token-based billing workflows using USDC on Base L2
⚡ Developer Benefits
OpenAI-compatible behavior for easier integration
MCP-oriented service under model-context-protocol
Token-based payment model aligned with Base L2 (USDC)
⚠️ Limitations
Provided metadata does not specify available MCP tools, toolCount, or concrete endpoint/function list beyond the “compute/health” reference.
OpenAI-compatible inference broker. Pay per token in USDC on Base L2.
https://hive-mcp-gateway.onrender.com/compute/mcp
HiveCompute
OpenAI-compatible inference broker. Pay per token in USDC on Base L2.
MCP server for HiveCompute — OpenAI-compatible inference router for the Hive agent economy. Chat completions, embeddings, and model listings. Hive routes to the cheapest qualifying model. Billed per token in USDC on Base L2. Real rails.
What this is
hive-mcp-compute is a Model Context Protocol (MCP) server that exposes the HiveCompute platform on the Hive Civilization to any MCP-compatible client (Claude Desktop, Cursor, Manus, etc.). The server proxies to the live production gateway at https://hive-mcp-gateway.onrender.com.
Protocol: MCP 2024-11-05 over Streamable-HTTP / JSON-RPC 2.0
x402 micropayments: every paid call produces a real on-chain settlement
Rails: USDC on Base L2 — real rails, no mocks
Author: Steve Rotzin · Hive Civilization · brand gold #C08D23
Endpoints
Path
Purpose
POST /mcp
JSON-RPC 2.0 / MCP 2024-11-05
GET /
HTML landing with comprehensive meta tags + JSON-LD