Mcp Hive Proxy — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Mcp Hive Proxy (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
This is the MCP-Hive Proxy. It can be loaded by any agentic host in order to access MCP-Hive and is a gateway to other MCP servers. To obtain credentials, and read further documentation, go to mcp-hive.com
The proxy can run in two modes:
Proxy a specific MCP server to your MCP client:
node src/proxy/mcpHiveProxy.ts --server <server-name> --local --credentials <credentials>Expose all available MCP servers through a single proxy with namespaced tools:
node src/proxy/mcpHiveProxy.ts --gateway --local --credentials <credentials>In gateway mode:
discoverServers, listTools, listResources, listPromptsserverName___toolName (e.g., validator___echo, accuweather___getWeather)| Flag | Description |
|---|---|
--server <name> | Proxy a specific MCP server (omit for gateway mode) |
--gateway | Explicitly enable gateway mode |
--http | Run the proxy in HTTP transport |
--port <port_num> | Port number to be used if HTTP-transport |
--credentials <id> | Consumer credentials for authentication |
--verbose | Enable verbose logging |
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.