Back to search
100
MCP live MCP 2026-07-28 streamable-http

HVTracker MCP

io.github.yugantm/hvtracker-mcp

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

Watch this dependency

Get before/after evidence when observed tools, schemas, authentication access, availability or the endpoint changes.

Inspect evidence and set up a watch Share public evidence report
Uptime
100.0%
4 direct probes · 30d
Response
797ms
last probe
Tools
8
callable
Resources
0
readable
Prompts
0
available
Primary URL
https://hvtracker.net/mcp
Score: 100/100
Handshake verified by our own probe.
why this score
pass Answers the MCP handshake 50/50
The handshake and the list calls succeeded on the primary URL.
pass Lists tools, resources or prompts 30/30
8 tools, 0 resources, 0 prompts returned.
pass 3 or more catalogue items 10/10
8 items in total; 3 or more earns these points.
pass Describes itself 10/10
95 characters; more than 30 earns these points.

Tools · 8

check_agent_trust

Get the HVTracker supply-chain trust profile for a tracked AI agent or framework.

verify_mcp_server

Pre-connect trust verdict for an MCP server, package, GitHub repo, or agent name before connecting an AI agent to it.

compare_agents

Compare two tracked AI agents side by side: trust scores, grades, runtime capabilities, and an evidence-based verdict.

search_agents

Search tracked AI agents and frameworks by name, repo, description, or category, ranked by trust score.

scan_stack

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.

list_categories

List the HVTracker categories with agent counts, so you can then pull a category's leaderboard.

get_leaderboard

Top tracked AI agents and MCP servers ranked by HVTrust score, optionally filtered to one category.

get_agent_history

90-day trust-score, grade, and rank history for one tracked agent — is it improving or declining?

How to use

Add to your Claude Desktop / Cursor / Cline MCP config:

{
  "mcpServers": {
    "hvtracker_mcp": {
      "url": "https://hvtracker.net/mcp",
      "transport": "streamable-http"
    }
  }
}

Or run it locally:

Runs locally from its npm package (v0.4.0). Add to your Claude Desktop / Cursor / Cline MCP config:

{
  "mcpServers": {
    "hvtracker_mcp": {
      "command": "npx",
      "args": [
        "-y",
        "hvtracker-mcp@0.4.0"
      ]
    }
  }
}

Runs locally from its PyPI package (v0.4.0). Add to your Claude Desktop / Cursor / Cline MCP config:

{
  "mcpServers": {
    "hvtracker_mcp": {
      "command": "uvx",
      "args": [
        "hvtracker-mcp@0.4.0"
      ]
    }
  }
}

Runs locally from its container image ghcr.io/yugantm/hvtracker-mcp:v0.4.0. Add to your Claude Desktop / Cursor / Cline MCP config:

{
  "mcpServers": {
    "hvtracker_mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/yugantm/hvtracker-mcp:v0.4.0"
      ]
    }
  }
}

Source: github.com/YugantM/hvtracker-mcp