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

AgentSecurityLens MCP Security Trust Check

NPM · AGENT-SECURITY-LENS · SCANNED AUG 3

MCP security trust-check for agents before installing MCPs, Skills or tools.

Available components

−10 this week 63 Trust /100
Trust breakdown (6 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 →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency45
Schema Quality & AI Usability60
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 752 tokens (~68/item across 11 items; 11 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage72
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 17% of tool parameters carry a description.Partial
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · agent-security-lens

# add to Claude Code
claude mcp add professor2k8-agent-security-lens -- npx -y agent-security-lens
# add to Codex CLI
codex mcp add professor2k8-agent-security-lens -- npx -y agent-security-lens
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "professor2k8-agent-security-lens": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "agent-security-lens"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add professor2k8-agent-security-lens --command npx --arg -y --arg agent-security-lens
# ~/.hermes/config.yaml
mcp_servers:
  professor2k8-agent-security-lens:
    command: "npx"
    args: ["-y", "agent-security-lens"]
// mcp.json
{
  "mcpServers": {
    "professor2k8-agent-security-lens": {
      "command": "npx",
      "args": [
        "-y",
        "agent-security-lens"
      ]
    }
  }
}
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.

  • 2 Aug 26 +15
    • Malware scan: unverified → pass security
  • 31 Jul 26 −7
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 −18
    • Malware scan: pass → unverified security
  • 27 Jul 26 +26
    • Tool coverage: unverified → 100 functional
    • First check of Tool coverage: 17 functional
    • First check of Schema quality: fail functional
    • First check of Schema quality: fair functional
    • First check of Schema quality: pass functional
  • 26 Jul 26 47

    First indexed and scored.

    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
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 3 Aug 2026 · Analysed npm/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 0 packages

0 packages in the resolved dependency tree.

MCP tools — 11 exposed · ~752 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.

Tool Tokens
check_component ~64

Check ASL online intelligence for a component and return an agent-readable install decision.

NameTypeReqDescription
component_namestring
component_typestring
install_commandstring
manifestobject|string
source_urlstring

No output schema declared.

No examples provided.

discover_workspace ~36

Discover Agent, MCP and Skill environments under a workspace path.

NameTypeReqDescription
max_depthnumber
workspace_pathstringyes

No output schema declared.

No examples provided.

get_install_policy ~38

Return the ASL machine-readable policy an autonomous agent should follow before installing MCPs, Skills, tools, prompt bundles, workflows or memory components.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_intelligence_status ~32

Return whether ASL MCP is using online cloud intelligence or local fallback, and whether the cloud API is reachable.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_research_status ~43

Check whether an unknown component submitted to ASL has been collected, scanned, reviewed, published, archived or is still pending.

NameTypeReqDescription
submission_idstringyes

No output schema declared.

No examples provided.

recommend_alternatives ~62

Return safer alternatives and a safe install plan for a component.

NameTypeReqDescription
component_namestring
component_typestring
install_commandstring
manifestobject|string
source_urlstring

No output schema declared.

No examples provided.

report_install_outcome ~97

Report what happened after an agent followed an ASL decision. Use this to improve ASL adoption metrics and recommendation quality.

NameTypeReqDescription
alternative_usedstring
component_namestring
component_typestring
decisionstring
error_summarystring
outcomestring
restriction_appliedboolean
source_urlstring

No output schema declared.

No examples provided.

review_before_install ~178

Query ASL intelligence before an autonomous agent installs or enables an MCP, Skill, tool, prompt bundle, workflow, memory component or install command.

NameTypeReqDescription
component_namestringComponent name, package name or display name.
component_typestring
install_commandstringCommand the agent plans to run, such as npx/uvx/docker.
manifestobject|stringMCP/Skill manifest or config snippet.
planned_usestringWhat the agent wants to use this component for.
requested_permissionsarrayPermissions the agent expects this component to need, such as shell, filesystem, network or browser.
source_urlstringGitHub, registry, npm, Docker or documentation URL.
submit_if_unknownbooleanQueue unknown components for ASL research.

No output schema declared.

No examples provided.

scan_workspace ~46

Discover and assess every Agent, MCP and Skill environment under a workspace path. Use this for local context only.

NameTypeReqDescription
max_depthnumber
workspace_pathstringyes

No output schema declared.

No examples provided.

submit_decision_feedback ~84

Submit feedback about whether an ASL decision was useful, wrong, missing an alternative, or too strict. Do not include secrets or private code.

NameTypeReqDescription
commentstring
component_namestring
component_typestring
decisionstring
feedback_typestring
ratingnumber

No output schema declared.

No examples provided.

submit_unknown_component ~72

Submit public metadata for an unknown component to the ASL research queue. Do not submit private file contents or secrets.

NameTypeReqDescription
component_namestring
component_typestring
install_commandstring
manifestobject|string
source_urlstring

No output schema declared.

No examples provided.