Safer Agentic AI MCP

Created By
Nell Watson15 days ago
SaferAgenticAI MCP brings the Safer Agentic AI safety framework to coding assistants over the Model Context Protocol. It serves 238 normative implementation patterns and 14 operational heuristics across all 16 safety suites (9 Drivers + 7 Inhibitors) through 12 read-only tools: search patterns, resolve requirements, map a task to the relevant safety guidance, and follow cross-references.
Overview

SaferAgenticAI MCP brings the Safer Agentic AI safety framework to coding assistants over the Model Context Protocol.

It serves 238 normative implementation patterns and 14 operational heuristics across all 16 safety suites (9 Drivers + 7 Inhibitors) through 12 read-only tools: search patterns, resolve requirements, map a task to the relevant safety guidance, and follow cross-references.

Highlights

  • Read-only, no auth, no external calls — framework data is bundled in the package
  • stdio transport · Python ≥3.10 · MIT licensed

Install

  uvx saferagenticai-mcp

(or pipx install saferagenticai-mcp)

Config

  {"mcpServers":{"saferagenticai":{"command":"uvx","args":["saferagenticai-mcp"]}}}

More: https://www.saferagenticai.org

Server Config

{
  "mcpServers": {
    "saferagenticai": {
      "type": "http",
      "url": "https://mcp.saferagenticai.org/mcp"
    }
  }
}
Project Info
Created At
15 days ago
Updated At
14 days ago
Author Name
Nell Watson
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Teardrop

9 days ago