Directory / MCP servers (protocol)

MCP servers (protocol)

Protocol · Model Context Protocol · 3/7 verified · Last checked 2026-10-16

The spec says hosts should get user consent before tool calls and treat tool descriptions as untrusted. HTTP servers use OAuth 2.1 with audience-bound tokens. Real safety depends on each host and server.

Overall: C (2.33 avg, 3/7 controls verified; capped from B because B needs 4 verified)

Lock this down first

Only install servers you trust, and never pass a server's token through to upstream APIs.

Scorecard

Criterion	Rating	Notes
Permission granularity	2/3	See sources.
Human approval gates	2/3	The spec's principles call for explicit user consent. Each host decides how to implement it.
Sandboxing	Unverified	Not confirmed in the docs we checked.
Secrets handling	3/3	OAuth 2.1 with PKCE and resource indicators. Token passthrough is forbidden.
Audit logs	Unverified	Not confirmed in the docs we checked.
Kill switch / interrupt	Unverified	Not confirmed in the docs we checked.
Network egress control	Unverified	Not confirmed in the docs we checked.

Unverified: Sandboxing, Audit logs, Kill switch / interrupt, Network egress control. That means we could not confirm it in public docs, not that it is missing.

Sources

Vendor? Request a correction. We review corrections within 7 days.