56 tagged Guardrails, measured the same way as everything else here.
Browse within: AI Safety 22LLM 14model-context-protocol 8ai-security 6agent-security 5audit-log 5mcp-server 5
MCP server Claude CodeCodexCursor +2
Let an LLM propose UPDATE/DELETE, then actually run it, measure the real before/after diff, and always roll back — so the human approves measured facts, not the model's claim. Runs locally from the @hyuga/llm-safe-sql npm package.
MCP server Claude CodeCodexCursor +2
MCP server "mcp-trustlayer" as configured in neelbarm/mcp-trustlayer. Runs locally from the mcp-trustlayer Python package.
MCP server Claude CodeCodexCursor +2
Cost-effective serverless computing. Runs locally from the cortex Python package.
MCP server Claude CodeCodexCursor +2
MCP server "mcp-guarded-tools" as configured in ridwanspace/mcp-guarded-tools. Runs locally from the mcp-guarded-tools npm package.
Bristlecone2026/bristlecone-logic
MCP server Claude CodeCodexCursor +2
Micro-settled utility tools for AI agents and MCP clients by Bristlecone Logic. Runs locally from the bristlecone-mcp Python package.
Creed-Space/creedspace-mcp-server
MCP server Claude CodeCodexCursor +2
Constitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication. Runs locally from the @creedspace/mcp-server npm package.