What it does
The gateway sits between an AI agent and MCP tools, applying a runtime security policy to each tool call. Its publisher describes tool-call-level control, so decisions can be made for individual calls rather than only for whole sessions.
The gateway also records an audit of agent actions. The publisher's description does not give further detail on setup, supported clients or the format of the audit records.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
ai.sealgate/gateway
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
v1.0.0As shown on registry.modelcontextprotocol.io when we last read it