MCP gateway between AI agents and their tools, the web and Matrix: three-layer prompt-injection defense, smaller tool lists and responses, gateway-enforced parameter and response guards, OAuth/DCR, and per-agent profiles
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add trentina -- uvx mcp-trentina-crunchtools~/.codex/config.toml
[mcp_servers.trentina]
command = "uvx"
args = ["mcp-trentina-crunchtools"]
# codex mcp add trentina -- uvx mcp-trentina-crunchtools~/.cursor/mcp.json
{
"mcpServers": {
"trentina": {
"command": "uvx",
"args": [
"mcp-trentina-crunchtools"
]
}
}
}.vscode/mcp.json
{
"servers": {
"trentina": {
"type": "stdio",
"command": "uvx",
"args": [
"mcp-trentina-crunchtools"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"trentina": {
"command": "uvx",
"args": [
"mcp-trentina-crunchtools"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"trentina": {
"command": "uvx",
"args": [
"mcp-trentina-crunchtools"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"trentina": {
"command": "uvx",
"args": [
"mcp-trentina-crunchtools"
]
}
}
}