Skip to content

HVTracker MCP

by YugantM · remote · local (npm, oci, pypi) · no sign-in to list tools · v0.4.0 · published by GitHub user YugantM

Pre-connect trust checks for AI agents and MCP servers using HVTracker's public trust registry.

Changes · 2
CompareRegistry entry

8 tools: 2 change things and 6 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http hvtracker https://hvtracker.net/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

8 tools

Changes things 2Claude Code: ask
  • scan_stackBulk pre-connect trust check for a whole dependency set — paste a requirements.txt, package.json, MCP client config, or a plain list and get a trust verdict per item plus a stack s…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Bulk pre-connect trust check for a whole dependency set — paste a requirements.txt, package.json, MCP client config, or a plain list and get a trust verdict per item plus a stack summary.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Scan Stack
  • verify_mcp_serverPre-connect trust verdict for an MCP server, package, GitHub repo, or agent name before connecting an AI agent to it.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Pre-connect trust verdict for an MCP server, package, GitHub repo, or agent name before connecting an AI agent to it.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Verify MCP Server
Only reads 6Claude Code: allow
  • check_agent_trustGet the HVTracker supply-chain trust profile for a tracked AI agent or framework.No findings

    Why it is in this group

    • The description's first verb is "get": a word for reading.
    Description, as the server wrote it
    Get the HVTracker supply-chain trust profile for a tracked AI agent or framework.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Check Agent Trust
  • compare_agentsCompare two tracked AI agents side by side: trust scores, grades, runtime capabilities, and an evidence-based verdict.No findings

    Why it is in this group

    • The name "compare_agents" says "compare": a word for reading.
    Description, as the server wrote it
    Compare two tracked AI agents side by side: trust scores, grades, runtime capabilities, and an evidence-based verdict.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Compare Agents
  • get_agent_history90-day trust-score, grade, and rank history for one tracked agent — is it improving or declining?No findings

    Why it is in this group

    • The name "get_agent_history" says "get": a word for reading.
    Description, as the server wrote it
    90-day trust-score, grade, and rank history for one tracked agent — is it improving or declining?

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Get Agent History
  • get_leaderboardTop tracked AI agents and MCP servers ranked by HVTrust score, optionally filtered to one category.No findings

    Why it is in this group

    • The name "get_leaderboard" says "get": a word for reading.
    Description, as the server wrote it
    Top tracked AI agents and MCP servers ranked by HVTrust score, optionally filtered to one category.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Get Leaderboard
  • list_categoriesList the HVTracker categories with agent counts, so you can then pull a category's leaderboard.No findings

    Why it is in this group

    • The name "list_categories" says "list": a word for reading.
    Description, as the server wrote it
    List the HVTracker categories with agent counts, so you can then pull a category's leaderboard.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: List Categories
  • search_agentsSearch tracked AI agents and frameworks by name, repo, description, or category, ranked by trust score.No findings

    Why it is in this group

    • The name "search_agents" says "search": a word for reading.
    Description, as the server wrote it
    Search tracked AI agents and frameworks by name, repo, description, or category, ranked by trust score.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Search Agents

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 0.4.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http hvtracker https://hvtracker.net/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__hvtracker__check_agent_trust",
      "mcp__hvtracker__compare_agents",
      "mcp__hvtracker__search_agents",
      "mcp__hvtracker__list_categories",
      "mcp__hvtracker__get_leaderboard",
      "mcp__hvtracker__get_agent_history"
    ],
    "ask": [
      "mcp__hvtracker__verify_mcp_server",
      "mcp__hvtracker__scan_stack"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as hvtracker. Review it before you use it.