Score any AI for trust across 10 dimensions; evaluate, monitor & govern LLMs and agents.
Connect Runs on your machine
claude mcp add trustmodel-mcp -e TRUSTMODEL_API_KEY=<TRUSTMODEL_API_KEY> -e TRUSTMODEL_BASE_URL=<TRUSTMODEL_BASE_URL> -e TRUSTMODEL_PROFILE=<TRUSTMODEL_PROFILE> -e TRUSTMODEL_GUARDRAIL_FAIL_MODE=<TRUSTMODEL_GUARDRAIL_FAIL_MODE> -- npx -y @trustmodel/[email protected]{
"mcpServers": {
"trustmodel-mcp": {
"command": "npx",
"args": [
"-y",
"@trustmodel/[email protected]"
],
"env": {
"TRUSTMODEL_API_KEY": "<TRUSTMODEL_API_KEY>",
"TRUSTMODEL_BASE_URL": "<TRUSTMODEL_BASE_URL>",
"TRUSTMODEL_PROFILE": "<TRUSTMODEL_PROFILE>",
"TRUSTMODEL_GUARDRAIL_FAIL_MODE": "<TRUSTMODEL_GUARDRAIL_FAIL_MODE>"
}
}
}
}{
"mcpServers": {
"trustmodel-mcp": {
"command": "npx",
"args": [
"-y",
"@trustmodel/[email protected]"
],
"env": {
"TRUSTMODEL_API_KEY": "<TRUSTMODEL_API_KEY>",
"TRUSTMODEL_BASE_URL": "<TRUSTMODEL_BASE_URL>",
"TRUSTMODEL_PROFILE": "<TRUSTMODEL_PROFILE>",
"TRUSTMODEL_GUARDRAIL_FAIL_MODE": "<TRUSTMODEL_GUARDRAIL_FAIL_MODE>"
}
}
}
}{
"servers": {
"trustmodel-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@trustmodel/[email protected]"
],
"env": {
"TRUSTMODEL_API_KEY": "<TRUSTMODEL_API_KEY>",
"TRUSTMODEL_BASE_URL": "<TRUSTMODEL_BASE_URL>",
"TRUSTMODEL_PROFILE": "<TRUSTMODEL_PROFILE>",
"TRUSTMODEL_GUARDRAIL_FAIL_MODE": "<TRUSTMODEL_GUARDRAIL_FAIL_MODE>"
}
}
}
}Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.
Tools
This server runs locally, so its tools are listed by your MCP client once it starts.
Environment variables
| Name | Description |
|---|---|
TRUSTMODEL_API_KEYOptional, secret | TrustModel API key (free — 5 credits / $500 at https://app.trustmodel.ai) for calibrated cloud scoring. Optional: the local trustmodel_evaluate_local and trustmodel_govern tools work without it. |
TRUSTMODEL_BASE_URLOptional | Override the TrustModel API base URL (default https://api.trustmodel.ai). |
TRUSTMODEL_PROFILEOptional | Tool profile: 'default' exposes the 7 daily-driver tools; 'security' / 'advanced' / 'all' expose all 23. |
TRUSTMODEL_GUARDRAIL_FAIL_MODEOptional | Behavior only when no HTTP response is received: fail_closed (default) or fail_open. HTTP refusals always block. |
Details
| Package | @trustmodel/[email protected] (NPM, stdio) |
| First published | 12 Nov 2026 |
| Last updated | 12 Nov 2026 |
| Registry name | io.github.pdxlab/trustmodel-mcp |
More ai and media servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.