AI Security Gateway's MCP Gateway extends the company's LLM proxy security features to agent tool calls, scanning MCP tools for poisoning attempts and redacting personally identifiable information in tool call arguments and results. It integrates with the broader AI Security Gateway platform, which provides PII redaction, budget enforcement, and prompt-injection defense across 600+ models from 8 AI providers. The MCP Gateway can run in AI Security Gateway's cloud or be deployed inside a customer's own VPC. It is currently in beta, gated behind a bearer-token API key.
Cognium trust score
30%
Tier
Unverified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-08-30.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.