TrustModel MCP Server — trust evaluation, red-team & governance for AI agents via the Model Context Protocol. Public canonical home of @trustmodel/mcp-server.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add trustmodel --env TRUSTMODEL_API_KEY='<TRUSTMODEL_API_KEY>' -- npx -y @trustmodel/mcp-server~/.codex/config.toml
[mcp_servers.trustmodel]
command = "npx"
args = ["-y", "@trustmodel/mcp-server"]
env = { TRUSTMODEL_API_KEY = "<TRUSTMODEL_API_KEY>" }
# codex mcp add trustmodel --env TRUSTMODEL_API_KEY='<TRUSTMODEL_API_KEY>' -- npx -y @trustmodel/mcp-server~/.cursor/mcp.json
{
"mcpServers": {
"trustmodel": {
"command": "npx",
"args": [
"-y",
"@trustmodel/mcp-server"
],
"env": {
"TRUSTMODEL_API_KEY": "<TRUSTMODEL_API_KEY>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"trustmodel": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@trustmodel/mcp-server"
],
"env": {
"TRUSTMODEL_API_KEY": "<TRUSTMODEL_API_KEY>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"trustmodel": {
"command": "npx",
"args": [
"-y",
"@trustmodel/mcp-server"
],
"env": {
"TRUSTMODEL_API_KEY": "<TRUSTMODEL_API_KEY>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"trustmodel": {
"command": "npx",
"args": [
"-y",
"@trustmodel/mcp-server"
],
"env": {
"TRUSTMODEL_API_KEY": "<TRUSTMODEL_API_KEY>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"trustmodel": {
"command": "npx",
"args": [
"-y",
"@trustmodel/mcp-server"
],
"env": {
"TRUSTMODEL_API_KEY": "<TRUSTMODEL_API_KEY>"
}
}
}
}Environment variables
TRUSTMODEL_API_KEY
Replace the placeholders with your own credentials and keep them out of version control.