MCPProxy runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 18 Sep 2026.
Local-first MCP proxy with BM25 tool discovery, security scanning, quarantine & ~99% token savings
We read the source, 21 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
if fs.Exists("/.dockerenv") || fs.Exists("/run/.containerenv") {
return filepath.Join(home, config.DefaultDataDir)
select {
case vm := <-oldAvailable:
instanceCount++
// Only keep instances up to newSize
if instanceCount <= newSize {
let process = Process()
".ssh", "id_rsa", "id_ed25519", "/etc/passwd", "/etc/shadow", ".aws/credential",
regexp.MustCompile(`(?i)(?:\.git-credentials|\.gitconfig|\.npmrc|\.pypirc|\.netrc)\b`),
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
MCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.
MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
Precision-first security scanning for Model Context Protocol servers.
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.
Security scanner and runtime proxy for MCP servers.
Discover and vet MCP servers: search 200K+ AI tools with security verification and schemas.
Answers built from our own checks of this server.