mcp-proxy
Bridge that exposes stdio MCP servers over HTTP/SSE, or vice versa. Run a local server remotely, or connect to a remote server as if it were local.
mcp-proxy solves the transport mismatch problem in MCP. Most local MCP servers use stdio transport, but some clients (especially cloud-hosted ones) can only speak HTTP or SSE. mcp-proxy wraps either side: point it at a stdio server and it exposes an HTTP endpoint; point it at a remote HTTP server and it exposes a stdio interface for clients that expect one. It handles the session management, reconnection logic, and request correlation that you would otherwise have to write yourself. For anyone bridging between self-hosted local tooling and a cloud Claude/ChatGPT client, mcp-proxy is usually in the path.
Similar Tools
MCP Inspector
Visual testing tool for Model Context Protocol servers. Like Postman for MCP - call tools, browse resources, and view real-time logs in a browser UI. Zero install via npx.
MCP CLI
Lightweight CLI for discovering and calling MCP servers. Dynamic tool discovery reduces token consumption from 47K to 400 tokens. Three subcommands: info, grep, call.
MCP Hub
Centralized manager for MCP servers. Connect once to localhost:37373 and access all your servers through a single endpoint. REST API, web UI, and VS Code config compatible.
Smithery
Registry and hosting platform for MCP servers. 6,000+ servers indexed. One-command install and configuration via CLI. Supports local and hosted deployments.
Get started with mcp-proxy
Bridge that exposes stdio MCP servers over HTTP/SSE, or vice versa. Run a local server remotely, or connect to a remote server as if it were local.
Try mcp-proxyGet weekly tool reviews
Honest takes on AI dev tools, frameworks, and infrastructure - delivered to your inbox.
Subscribe FreeMore MCP Tools Tools
MCP Inspector
Visual testing tool for Model Context Protocol servers. Like Postman for MCP - call tools, browse resources, and view real-time logs in a browser UI. Zero install via npx.
MCP CLI
Lightweight CLI for discovering and calling MCP servers. Dynamic tool discovery reduces token consumption from 47K to 400 tokens. Three subcommands: info, grep, call.
MCP Hub
Centralized manager for MCP servers. Connect once to localhost:37373 and access all your servers through a single endpoint. REST API, web UI, and VS Code config compatible.
Related Guides
Claude Code Setup Guide
Configure Claude Code for maximum productivity -- CLAUDE.md, sub-agents, MCP servers, and autonomous workflows.
AI AgentsMCP Servers Explained
What MCP servers are, how they work, and how to build your own in 5 minutes.
AI AgentsClaude Code Complete Course
A complete, citation-backed Claude Code course with setup, prompting systems, MCP, CI, security, cost controls, and capstone workflows.
ai-developmentRelated Posts

OpenCode Developer Guide: The Open Source AI Coding Agent with 160K Stars
OpenCode is the fastest-growing open-source AI coding agent - 160K GitHub stars, 7.5M monthly users, 75+ model providers...
WebMCP: Google's Browser Standard That Lets AI Agents Use Websites as Tools
Chrome 149 ships an origin trial for WebMCP - a proposed web standard that lets developers expose JavaScript functions a...
Headroom: Compress Agent Tool Output Before It Reaches the LLM
Headroom is a context compression layer that intercepts your AI agent's tool outputs and strips 60-95% of the tokens bef...
Headroom: The Context Compression Layer Saving 60-95% of Your LLM Tokens
Headroom is an open-source context compression tool that reduces tokens sent to LLMs by 60-95%, available as a Python li...

The Agent Security Checklist I Use Before Connecting Tools
Before an AI agent gets tools, files, APIs, MCP servers, or deployment access, decide what it can read, write, call, log...

Prompt Injection in Agent Apps: The Practical Version
Prompt injection stops being an abstract LLM risk once an agent can call tools. The practical defense is data boundaries...
