HVTracker MCP

–Likes are community signals, not a measured score.

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

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

Author	io.github.YugantM
Access	mixed
Publisher key required	No
Measured state	Deep-tested
L1 liveness	alive
L1 latency	257 ms
Last measured	2026-10-26

Add to your agent

Copy this into your MCP client config:

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

Measured tools (8)

check_agent_trust read-only
Get the HVTracker supply-chain trust profile for a tracked AI agent or framework.
Parameters:
- name_or_repo (required) — string
Hints: read-only yes · destructive no · idempotent yes · open-world yes
verify_mcp_server read-only
Pre-connect trust verdict for an MCP server, package, GitHub repo, or agent name before connecting an AI agent to it.
Parameters:
- server (required) — string
Hints: read-only yes · destructive no · idempotent yes · open-world yes
compare_agents read-only
Compare two tracked AI agents side by side: trust scores, grades, runtime capabilities, and an evidence-based verdict.
Parameters:
- a (required) — string
- b (required) — string
Hints: read-only yes · destructive no · idempotent yes · open-world yes
search_agents read-only
Search tracked AI agents and frameworks by name, repo, description, or category, ranked by trust score.
Parameters:
- limit — integer
- query — string
- category — string
Hints: read-only yes · destructive no · idempotent yes · open-world yes
scan_stack read-only
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.
Parameters:
- input (required) — string
Hints: read-only yes · destructive no · idempotent yes · open-world yes
list_categories read-only
List the HVTracker categories with agent counts, so you can then pull a category's leaderboard.
Hints: read-only yes · destructive no · idempotent yes · open-world yes
get_leaderboard read-only
Top tracked AI agents and MCP servers ranked by HVTrust score, optionally filtered to one category.
Parameters:
- limit — integer
- category — string
Hints: read-only yes · destructive no · idempotent yes · open-world yes
get_agent_history read-only
90-day trust-score, grade, and rank history for one tracked agent — is it improving or declining?
Parameters:
- name_or_repo (required) — string
Hints: read-only yes · destructive no · idempotent yes · open-world yes

Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.