gsep mcp for VS Code
io.github.gsepcore/gsep-mcp
AI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts.
client:VS Code
transport:stdio
runtime:npm
Install gsep mcp in VS Code
.vscode/mcp.json
{
"inputs": [
{
"type": "promptString",
"id": "anthropic-api-key",
"description": "ANTHROPIC_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "openai-api-key",
"description": "OPENAI_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "ollama-host",
"description": "OLLAMA_HOST",
"password": true
},
{
"type": "promptString",
"id": "gsep-preset",
"description": "GSEP_PRESET",
"password": true
}
],
"servers": {
"gsep-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@gsep/mcp"
],
"env": {
"ANTHROPIC_API_KEY": "${input:anthropic-api-key}",
"OPENAI_API_KEY": "${input:openai-api-key}",
"OLLAMA_HOST": "${input:ollama-host}",
"GSEP_PRESET": "${input:gsep-preset}"
}
}
}
}
VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs