Gsep MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 50 installs a week from npm. Last commit 24 May 2026.
AI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts.
We read the source, 5 h ago · rules 3dff92dd89df
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
command: 'rm -rf /home/user/projects',
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const storagePath = path.join(config.storagePath, genomeId, 'gsep.sqlite');
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Gsep MCP and you get told the day something new turns up.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add gsep-mcp -- npx -y @gsep/mcp
{
"mcpServers": {
"gsep-mcp": {
"args": [
"-y",
"@gsep/mcp"
],
"command": "npx"
}
}
}
[mcp_servers.gsep-mcp]
command = "npx"
args = ["-y", "@gsep/mcp"]
{
"mcpServers": {
"gsep-mcp": {
"args": [
"-y",
"@gsep/mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"gsep-mcp": {
"args": [
"-y",
"@gsep/mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
ANTHROPIC_API_KEY (Anthropic API key (use this OR OPENAI_API_KEY OR OLLAMA_HOST)), OPENAI_API_KEY (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)).
The author declared them in the registry entry; get the values from the project itself.
Multi-agent LLM security layer detecting prompt injection and jailbreaks.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Thin MCP and CLI proxy for AI agent and MCP security auditing via a hosted backend
SupraWall security gateway for AI agents. Provides deterministic guardrails for MCP agents.
Security scanner for third-party AI agent-skill files (SKILL.md, hooks, scripts) via MCP.
AI Agent Guardrails MCP server - security layer
Security gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.
AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening
Answers built from our own checks of this server.