Runtime security gateway and FastMCP server that protects MCP clients from tool poisoning, prompt injection, and unauthorized tool schema changes through policy enforcement, fail-closed scanning, and human approval gates.
Enables safe use of any MCP server by proxying and live-scanning all tool requests and responses, blocking or redacting poison descriptions, indirect prompt injection, malicious arguments, and unauthorized destinations.
Security gateway for MCP tool calls. Sits between your LLM client and MCP servers, enforcing per-tool policies (allow/block/approve/read-only), logging every call, and pausing dangerous operations for human approval in terminal or Slack.
Proxies MCP traffic between a client and a downstream server to enforce runtime policies on tool declarations, call arguments, and results, including allowlisting, sandboxing, secret and egress controls, and injection detection. It also includes a deterministic benchmark for measuring which security controls stop which attacks.