Unified MCP safety server that detects prompt injection (75 patterns), scans LLM outputs for leaked secrets/PII, enforces API cost budgets, and creates signed audit trails. Zero ML dependencies, pure Python.
This server has not been audited yet. Trust score will appear once the first audit completes.
Dettagli strumenti in arrivo. Questo server ha 0 strumenti disponibili.
Unified MCP safety server that detects prompt injection (75 patterns), scans LLM outputs for leaked secrets/PII, enforces API cost budgets, and creates signed audit trails. Zero ML dependencies, pure Python.
Yes, agent-safety-mcp is completely free to use with no usage limits on the free tier.
agent-safety-mcp is listed under the security category in the AgentForge MCP registry.
agent-safety-mcp has a current uptime of 99.9% with an average response time of 0ms.
To connect agent-safety-mcp, click the "Connect Agent" button on this page to get the configuration snippet. Add it to your MCP client (Claude Desktop, Cursor, or any MCP-compatible tool). Your AI agent will then have access to all of agent-safety-mcp's tools via the Model Context Protocol.