MCP Tools DirectoryAbout this integration
AI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts.
- Transport
- stdio
- Authentication
- unknown
- Initial setup
- credentials
- Runtime
- unattended
- Evidence
- documented
- Version
- 1.0.0
- Package
- @gsep/mcp
- Last compatibility test
- Not independently tested
Connect your agent
@gsep/mcpPublisher README and package manifest reviewed offline; the package and integration endpoint were not executed or independently security-audited. Authentication is provider-dependent and therefore classified as unknown; claimed protection effectiveness was not tested.
Capabilities: Prompt scanning, Action scanning, Protected LLM middleware
Connected profiles
Additional details
io.github.gsepcore/gsep-mcp
Source ↗ · Checked 2026-09-171.0.0
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17npm
Source ↗ · Checked 2026-09-17@gsep/mcp
Source ↗ · Checked 2026-09-191.0.9
Source ↗ · Checked 2026-09-19The documented default stdio transport is launched by the MCP client as a subprocess.
Source ↗ · Checked 2026-09-19Provider authentication depends on configuration: local Ollama needs no key, while hosted model providers use API keys.
Source ↗ · Checked 2026-09-19Desktop and IDE clients launch the package with npx and provider environment configuration.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19