io.github.gsepcore/gsep-mcp

io.github.gsepcore/gsep-mcp·v1.0.0·Security

Quality Score

/100

AI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts.

Repository →

§01 Install

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "gsep-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@gsep/mcp"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<your-anthropic_api_key>",
        "OPENAI_API_KEY": "<your-openai_api_key>",
        "OLLAMA_HOST": "<ollama_host>",
        "GSEP_PRESET": "<gsep_preset>"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "gsep-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@gsep/mcp"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<your-anthropic_api_key>",
        "OPENAI_API_KEY": "<your-openai_api_key>",
        "OLLAMA_HOST": "<ollama_host>",
        "GSEP_PRESET": "<gsep_preset>"
      }
    }
  }
}

Cline (cline_mcp_settings.json)

npx -y @gsep/mcp

§02 Environment variables

ANTHROPIC_API_KEY

secret

Anthropic API key (use this OR OPENAI_API_KEY OR OLLAMA_HOST)

OPENAI_API_KEY

secret

OpenAI API key (use this OR ANTHROPIC_API_KEY OR OLLAMA_HOST)

OLLAMA_HOST

Ollama server URL for local models (e.g. http://localhost:11434)

GSEP_PRESET

Intelligence preset: minimal, standard, conscious, or full (default: full)

§03 MCP Quality Score · methodology

freshness

completeness

installability

documentation

stability

§04 Alternatives in Security

Helixar Security

ai.helixar/mcp

Security tools for AI agents: scan MCP servers, validate HDP delegation chains, audit releases.

ai.smithery/Nekzus-npm-sentinel-mcp

Provide AI-powered real-time analysis and intelligence on NPM packages, including security, depend…

app.zenable/zenable

Zenable cleans up sloppy AI code and prevents vulnerabilities with deterministic guardrails