{"id":"309f8e99-26c6-499a-b07e-55d8a8e8ec4f","slug":"cordum","kind":"mcp","name":"cordum","summary":"The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.","owner":"cordum-io","repoUrl":"https://github.com/cordum-io/cordum","license":null,"licenseTier":"unlicensed","trust":"community","stars":509,"match":null,"fewStars":false,"format":"mcp","createdAt":"2026-01-11T16:56:02.000Z","addedAt":"2026-10-14T05:13:15.768Z","logoUrl":"https://avatars.githubusercontent.com/u/248097825?v=4","linkOnly":true,"collection":null,"skillPath":null,"categories":["cloud-infra","memory-knowledge"],"tags":["ai-orchestration","ai-safety","autonomous-agents","governance","llm-agents","workflow-engine","agent-framework","agentic-ai"],"runtime":"go","local":false,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-15T02:54:43.479Z","sample":false,"url":"https://conduits.dev/tools/cordum","language":"Go","transports":["stdio"],"install":{},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":""}