News · curated 11 Aug 2026
MCP support: OpenAgent as an MCP client
First reported openagent.in
Coverage timeline
Single-source analysis — first reported, latest, and curated coincide.
Why it matters
OpenAgent's control set names concrete MCP-specific threats defenders must mitigate — tool-description rug-pulls, prompt injection embedded in tool responses, and over-scoped tool access — and illustrates a design pattern for hardening agentic MCP clients.
OpenAgent, a commercial AI support platform, describes its MCP client implementation and the security controls it wraps around the raw Model Context Protocol: per-tool admin approval, 'rug-pull' defense that re-flags tools when a server silently changes tool descriptions or input schemas, AES-256-GCM encrypted credentials, a PII-redacted audit log, and an untrusted-output marker that prefixes tool results with a warning to the LLM not to follow embedded instructions.