continue lets users wire in MCP servers as tools, which raises a before-you-connect question: can we show how trustworthy a given MCP server is first?
there's a public TrustScore for ~19.7K MCP servers/agents today. an optional check could surface a server's score (+ cert) when it's added, and let the user gate on a threshold. it's a lookup against our small MIT service / public index (trustmodel), no core change.
off by default, opt-in, metadata only.
is a pre-connect trust signal for MCP servers something continue would want to surface? glad to send a reference. https://trustmodel.ai/verify
continue lets users wire in MCP servers as tools, which raises a before-you-connect question: can we show how trustworthy a given MCP server is first?
there's a public TrustScore for ~19.7K MCP servers/agents today. an optional check could surface a server's score (+ cert) when it's added, and let the user gate on a threshold. it's a lookup against our small MIT service / public index (trustmodel), no core change.
off by default, opt-in, metadata only.
is a pre-connect trust signal for MCP servers something continue would want to surface? glad to send a reference. https://trustmodel.ai/verify