Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.karlmehta/trustmodel-mcp

NPM · @TRUSTMODEL/MCP-SERVER · SCANNED SEP 20

Score any AI for trust across 10 dimensions; evaluate, monitor & govern LLMs and agents.

0 this week 79 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security89
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects js-yaml 4.1.1, reached via @microsoft/agent-governance-sdk > js-yaml. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 35 of 109 dependencies flagged as unhealthy (1 deprecated). View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability70
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1170 tokens (~195/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management93
  • Stability observed for 28 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the io.github.karlmehta/trustmodel-mcp server?

io.github.karlmehta/trustmodel-mcp runs locally as an npm package, launched with npx -y @trustmodel/mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @trustmodel/mcp-server

# add to Claude Code
claude mcp add karlmehta-trustmodel-mcp -- npx -y @trustmodel/mcp-server
// .cursor/mcp.json
{
  "mcpServers": {
    "karlmehta-trustmodel-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@trustmodel/mcp-server"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "karlmehta-trustmodel-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@trustmodel/mcp-server"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add karlmehta-trustmodel-mcp -- npx -y @trustmodel/mcp-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "karlmehta-trustmodel-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@trustmodel/mcp-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add karlmehta-trustmodel-mcp --command npx --arg -y --arg @trustmodel/mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  karlmehta-trustmodel-mcp:
    command: "npx"
    args: ["-y", "@trustmodel/mcp-server"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "karlmehta-trustmodel-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@trustmodel/mcp-server"
      ]
    }
  }
}
# add to Vellum
assistant mcp add karlmehta-trustmodel-mcp -t stdio -c npx -a -y @trustmodel/mcp-server
// mcp.json
{
  "mcpServers": {
    "karlmehta-trustmodel-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@trustmodel/mcp-server"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 15 Sept 26 0
    • Stability: 0.97 → pass security
  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 −2
    • CVE-2026-84375 affects this package: high security
    • Stability: pass → 0.80 functional
  • 8 Sept 26 0
    • Stability: 0.97 → pass security
  • 7 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/@trustmodel/mcp-server@0.2.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 4 findings
ID CVE Severity Vector Fix available
GHSA-2883-xcg3-v3hh CVE-2026-84375 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
GHSA-52cp-r559-cp3m CVE-2026-59869 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
GHSA-5p4m-2wfm-xmqj high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
GHSA-h67p-54hq-rp68 CVE-2026-53550 medium CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 109 packages
Packages resolved 109
Deprecated 1
Stale 34
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~1,170 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
trustmodel_evaluate_local ~150

Score AI output locally across the 10 TrustModel dimensions (safety, fairness, accuracy, privacy, transparency, robustness, accountability, explainability, compliance, reliability) and roll it into a 0-100 TrustScore. NO API key required — runs on this machine with a transparent heuristic judge. Returns trust_score, grade, per-dimension scores, and violations. Local scores are uncalibrated; use trustmodel_evaluate (cloud, needs a free TRUSTMODEL_API_KEY) for a calibrated, audit-ready score.

NameTypeReqDescription
contextstringOptional context the output was produced in (improves judging).
outputstringyesThe AI output text to score.

No output schema declared.

No examples provided.

trustmodel_govern ~162

Check text against a governance policy pack and decide allow/block, locally. NO API key required. `policy` is a built-in pack id — eu-ai-act (default), nist-ai-rmf, nyc-ll144, or owasp-llm. Returns allowed/blocked, the policy id, and the list of rule violations (pattern and dimension rules). Use before letting AI output reach a user or another tool.

NameTypeReqDescription
contextstringOptional context the output was produced in.
policystringPolicy pack id: eu-ai-act (default), nist-ai-rmf, nyc-ll144, owasp-llm.
textstringyesThe text/output to check against the policy.

No output schema declared.

No examples provided.

trustmodel_score ~60

Get the current trust score / detail for a previous LLM evaluation created via trustmodel_evaluate. Takes an integer evaluation_id and returns the evaluation detail including scores.

NameTypeReqDescription
evaluation_idyesInteger evaluation ID returned from a previous trustmodel_evaluate call.

No output schema declared.

No examples provided.

trustmodel_trace_finalize ~251

Close an active trace session, serialize the captured steps, upload to TrustModel cloud storage, and auto-create an agentic evaluation run. Returns both a file_path (for record-keeping / retry) and an evaluation_run_id that can be polled with trustmodel_score_agent.

NameTypeReqDescription
actual_outcomestringOptional description of what actually happened.
agent_frameworkstringOverride `agent_framework` provided at trace_start.
agent_modelstringOverride `agent_model` provided at trace_start.
expected_outcomestringOverride `expected_outcome` provided at trace_start.
final_responsestringThe final user-facing answer from the agent.
goalstringOverride `goal` if the agent learned more at runtime.
goal_achievedbooleanWhether the agent achieved its goal.
namestringOverride `name` provided at trace_start.
successbooleanWhether the run is considered successful overall.
total_duration_msintegerTotal execution time in ms. If omitted, computed from step durations.
trace_idstringyesTrace handle returned by trustmodel_trace_start.

No output schema declared.

No examples provided.

trustmodel_trace_start ~235

Open a new agent-trace capture session. Returns a trace_id that must be passed to every trustmodel_trace_step and the final trustmodel_trace_finalize. Capture steps (thoughts, tool calls, tool results, responses) as your agent executes; finalize when done to upload + auto-create an evaluation run.

NameTypeReqDescription
agent_frameworkstringyesFramework the agent is built with (e.g. 'langchain', 'crewai', 'claude-code', 'custom').
agent_modelstringUnderlying LLM the agent is using (e.g. 'gpt-4o', 'claude-sonnet-4-5').
expected_outcomestringOptional description of the expected outcome.
goalstringyesWhat the agent is trying to achieve. Required; feeds the evaluation run.
metadataobjectFree-form passthrough metadata stored inside the trace file.
namestringyesDisplay name for the evaluation run (shown in TrustModel UI).
user_querystringOriginal user prompt that triggered the run, if different from `goal`.

No output schema declared.

No examples provided.

trustmodel_trace_step ~312

Record a single step in an active trace session. Call once per reasoning step, tool call, tool result, or user-facing response. Step numbers are auto-assigned (1-based). Requires a trace_id from trustmodel_trace_start.

NameTypeReqDescription
contentstringyesHuman-readable text for this step. Empty string allowed.
duration_msintegerHow long this step took, in milliseconds.
input_tokensintegerInput token count for this step.
model_usedstringModel used for this step's reasoning.
output_tokensintegerOutput token count for this step.
step_typestringyesKind of step: 'thought'/'think' (reasoning), 'tool_call', 'tool_result', 'observation', 'decision', 'error', 'human_input', 'response'/'final_answer' (user-facing output).
timestampstringISO 8601 timestamp. Defaults to the current time if omitted.
tool_argsobjectArguments passed to the tool (use with step_type='tool_call').
tool_call_successbooleanWhether the tool call succeeded (use with step_type='tool_result').
tool_namestringName of the tool invoked (use with step_type='tool_call' or 'tool_result').
tool_resultResult returned by the tool (use with step_type='tool_result').
trace_idstringyesTrace handle returned by trustmodel_trace_start.

No output schema declared.

No examples provided.

Common questions

What is the io.github.karlmehta/trustmodel-mcp server?

io.github.karlmehta/trustmodel-mcp is listed in the public MCP registry as io.github.karlmehta/trustmodel-mcp. Score any AI for trust across 10 dimensions; evaluate, monitor & govern LLMs and agents. This page covers its npm package (@trustmodel/mcp-server).

Is the io.github.karlmehta/trustmodel-mcp server safe to use?

io.github.karlmehta/trustmodel-mcp scores 79 out of 100 on VerifyMCP. We recorded 4 known advisories against it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.karlmehta/trustmodel-mcp server expose?

io.github.karlmehta/trustmodel-mcp exposes 6 tools: trustmodel_score, trustmodel_trace_start, trustmodel_trace_step, trustmodel_trace_finalize, trustmodel_evaluate_local, trustmodel_govern. Their descriptions and schemas cost roughly 1,170 tokens of context every time the server is loaded.

Is the io.github.karlmehta/trustmodel-mcp server still maintained?

io.github.karlmehta/trustmodel-mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.karlmehta/trustmodel-mcp server under?

io.github.karlmehta/trustmodel-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.