Supercharge AI agents safely with mcpproxy-go, for founders using AI tools.
intermediateโฑ 30 minutes๐ต Free (self-hosted)
292 stars37 forksGoQuality 8/10Updated 7/15/2026100% free ยท open source
What it is
Protect your AI agents with a secure proxy.
What you can make with it
Secure integrations like connecting your Stripe webhook to a Notion database without exposing your AI to unauthorized access.
How it helps
It helps you supercharge your AI agents safely, without compromising sensitive data or functionality.
Real use case example
"A founder building an e-commerce platform wants to automate the process of updating stock levels in Notion when a new order is received. First, they set up an mcpproxy-go instance and secure it with their API token. Next, they configure a webhook to trigger the proxy when a new order is placed, and finally, they set up a connection between the proxy and their Notion database."
If you're new
When you're just starting with AI and want to ensure your integrations are secure without much technical expertise.
If you're senior
When you need to protect sensitive data or functionality and want to ensure your AI integrations are scalable and secure.
Common confusion cleared up
mcpproxy-go is not a replacement for a full-fledged security solution, but rather a secure way to connect and control your AI agents.
Best inside these AI tools
Claude DesktopCursorCodex CLI
Pairs with
Claude APIStripe webhookNotion database
Why we list it on WorkflowStacks: A marketplace of AI tools includes this to provide a safe and secure method for using AI agents, without the need for extensive security expertise.
What it does
mcpproxy-go supercharges AI agents by providing a safe and efficient proxy server to manage and optimize their interactions
Install / run
go get github.com/smart-mcp-proxy/mcpproxy-go/cmd/mcpproxy-go
When to use it
โขWhen building AI-powered applications that require secure and controlled access to external services
โขWhen needing to optimize AI agent performance by caching, rate limiting, or load balancing
โขWhen developing multi-agent systems that require a centralized proxy to manage their interactions
Quick start
1Run the proxy server using the command `mcpproxy-go -config config.yml`
2Edit the `config.yml` file to configure the proxy server settings, such as the upstream URL and authentication credentials
3Use the `mcpproxy-go` command with the `-help` flag to view available options and flags
4Test the proxy server by sending a request to `http://localhost:8080` (default port)
5Modify the `config.yml` file to enable features like caching, rate limiting, or load balancing
Heads up: The `mcpproxy-go` command requires a valid `config.yml` file to be present in the current working directory, and the file must contain the necessary configuration settings, such as the upstream URL and authentication credentials
Saves to your device
Topics
ai
ai-agents
audit-logging
bm25
cli
context-window
developer-tools
docker
golang
llm
llm-tools
local-first
mcp
mcp-proxy
mcp-server
model-context-protocol
proxy-server
security
tool-routing
web-ui
What's inside โ free to inspect
No purchase needed
Read the entire source before you build โ unlike paid marketplaces that hide it behind a buy button.