- Conduid
- Marketplace
- #information-flow-control
MCP servers tagged information-flow-control
6 live MCP servers tagged "information-flow-control", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with information-flow-control.
Catraca
Provenance-aware authorisation for LLM agent tool calls. Denies a call when a consequential argument came from untrusted content. Stdlib only.
Navra
Secure MCP gateway for AI agents — deny-wins ACLs, IFC, in-process ML safety, 138 Kani proofs
Elliott
Standalone TypeScript framework for composing secure personal AI agents from one universal primitive — the Component. Manifest-first discovery, capability grants, orthogonal model…
ODIN Project
Odin - Zero Trust AI Agent. Open-source autonomous LLM agent with CaMeL dual-LLM, IFC taint tracking, DID-based identity, 3-ring sandbox, 5-state circuit breaker, and 3-phase cogn…
Trifecta
Find and block the lethal trifecta that forms across your MCP servers.
Still Untrusted
From-scratch TypeScript reimplementation of Microsoft Agent Framework's FIDES label algebra, checked against its spec.