Trustmodel MCP
io.github.pdxlab/trustmodel-mcp
Score any AI for trust across 10 dimensions; evaluate, monitor & govern LLMs and agents.
Connect this server
Add this to your MCP client config — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor).Suits: Claude Desktop · Cursor.
{
"mcpServers": {
"trustmodel-mcp": {
"command": "npx",
"args": [
"-y",
"@trustmodel/mcp-server@0.2.2"
],
"env": {
"TRUSTMODEL_API_KEY": "<your TRUSTMODEL_API_KEY>",
"TRUSTMODEL_PROFILE": "default",
"TRUSTMODEL_GUARDRAIL_FAIL_MODE": "fail_closed"
}
}
}
}- TRUSTMODEL_API_KEYsecretTrustModel 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_PROFILETool profile: 'default' exposes the 7 daily-driver tools; 'security' / 'advanced' / 'all' expose all 23.
- TRUSTMODEL_GUARDRAIL_FAIL_MODEBehavior only when no HTTP response is received: fail_closed (default) or fail_open. HTTP refusals always block.
A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.
- Category
- AI & Agents
- Version
- 0.2.2
- Registry
- active
- Published
- 11/12/2026
More AI & Agents servers
Browse all AI & Agents →LAHZE - Persian AI Memory Platform
webiro
Persian-first geo-memory platform: discover places, draft and publish Persian-only memories.
Penfield Memory
penfieldlabs
Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.
Perf MCP
Perf-Technology
Fact-check and fix AI outputs. Hallucination detection, schema validation, auto-repair.
Kit Memory Demo
PeterAtPondo
Continuity for agents: a live memory you can read and cite right now, outliving the context window.
MCP Light Memory
PeterPirog
Local-first persistent memory for coding agents and MCP clients.
Touchstone MCP
petrkrulis2022
Dated SIU, the benchmark price of AI inference work: one free tool, three paid via x402.
Add the badge to your site
Show visitors that Trustmodel MCP is listed here — it’s also the link we check for a free listing.
HTML — for your website
<a href="https://serverdex.io/server/io-github-pdxlab-trustmodel-mcp?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="Trustmodel MCP — listed on Serverdex" width="123" height="40" loading="lazy"></a>Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.
Markdown — for your README
[](https://serverdex.io/server/io-github-pdxlab-trustmodel-mcp?utm_source=badge)Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.