Not sure. Our big org, banned MCPs because they are unsafe, and they have no way to enforce only certain MCPs (in github copilot).

▲

thenewnewguy 5 hours ago | parent | next [-]

But skills where you tell the LLM to shell out to some random command are safe? I'm not sure I understand the logic.

	▲	toomuchtodo 5 hours ago \| parent \| next [-]
		You can control an execution context in a superior manner than a rando MCP server. MCP Security 2026: 30 CVEs in 60 Days - https://news.ycombinator.com/item?id=47356600 - March 2026 (securing this use case is a component of my work in a regulated industry and enterprise)
	▲	newswasboring 4 hours ago \| parent \| prev [-]
		I think big companies already protect against random commands causing damage. Work laptops are tightly controlled for both networking and software.

▲

mbreese 5 hours ago | parent | prev | next [-]

Isn’t it possible to proxy LLM communication and strip out unwanted MCP tool calls from conversations? I mean if you’re going to ban MCPs, you’re probably banning any CLI tooling too, right?

	▲	systima 5 hours ago \| parent [-]
		Maybe https://usepec.eu ?

▲

thecopy 4 hours ago | parent | prev | next [-]

Shameless plug: im working on a product that aims to solve this: https://www.gatana.ai/

	▲	brabel an hour ago \| parent [-]
		Who isn't?

▲

yoyohello13 5 hours ago | parent | prev [-]

We only allow custom MCP servers.