MCPLow riskUnclaimed

Yagami AI Context Firewall

Open-source AI context firewall for governed model, retrieval, memory, and tool access.

MatthewTracymatthewtracy/yagami★ 1Updated Oct 6, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.MatthewTracy/yagami",
  "description": "Open-source AI context firewall for governed model, retrieval, memory, and tool access.",
  "title": "Yagami AI Context Firewall",
  "repository": {
    "url": "https://github.com/MatthewTracy/yagami",
    "source": "github"
  },
  "version": "0.8.3",
  "websiteUrl": "https://matthewtracy.github.io/yagami/",
  "packages": [
    {
      "registryType": "pypi",
      "registryBaseUrl": "https://pypi.org",
      "identifier": "yagami",
      "version": "0.8.3",
      "runtimeHint": "uvx",
      "transport": {
        "type": "streamable-http",
        "url": "http://127.0.0.1:8000/mcp"
      },
      "packageArguments": [
        {
          "value": "serve",
          "type": "positional"
        },
        {
          "value": "127.0.0.1",
          "type": "named",
          "name": "--host"
        },
        {
          "value": "8000",
          "type": "named",
          "name": "--port"
        }
      ],
      "environmentVariables": [
        {
          "value": "true",
          "name": "YAGAMI_HEADLESS"
        },
        {
          "value": "true",
          "name": "YAGAMI_MCP_SERVER_ENABLED"
        },
        {
          "value": "false",
          "name": "YAGAMI_REQUIRE_AUTH"
        }
      ]
    }
  ],
  "_meta": {
    "io.modelcontextprotocol.registry/publisher-provided": {
      "documentation": "https://matthewtracy.github.io/yagami/integrations/",
      "license": "MIT",
      "privacy": "Telemetry is disabled by default; evidence is content-free."
    }
  }
}

Permissions

DeclaredDetected
Runs code—python
Installs—pypi:yagami@0.8.3
Runs install scripts—None
NetworkNoneNone
Needs credentialsNoneNone
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #10.8.3latestOct 7, 2026