io.github.yugantm/hvtracker-mcp
HVTracker MCP is a supply-chain trust verification server that lets you assess the safety and trustworthiness of AI agents, MCP servers, and frameworks before connecting to them.
Verify MCP Server Trust (
verify_mcp_server): Get a pre-connect trust verdict for an MCP server or AI agent by providing a GitHub owner/repo, GitHub URL, npm/PyPI package name, display name, slug, or MCP server URL — helping you decide whether it's safe to connect.Check Agent Trust Profile (
check_agent_trust): Retrieve a detailed HVTracker trust profile for a specific tracked AI agent or framework by name or repository identifier.Search the Agent Registry (
search_agents): Search the HVTracker registry of tracked AI agents and frameworks by name, repository, description, or category, with configurable result limits.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@io.github.yugantm/hvtracker-mcp verify trust for the GitHub MCP server"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
HVTracker MCP
MCP server for checking supply-chain trust before connecting to AI agents, frameworks, or MCP servers.
The hosted remote server is:
{
"mcpServers": {
"hvtracker": {
"url": "https://hvtracker.net/mcp"
}
}
}This repository also provides a local stdio package for clients that prefer package-based installation.
Tools
verify_mcp_server: pre-connect trust verdict for an MCP server, package, GitHub repo, or agent name.check_agent_trust: trust profile for a tracked AI agent or framework — incl. runtime capabilities (MCP status, providers, plugin surface, provenance drift) and the URL of its Ed25519-signed trust credential.compare_agents: two agents side by side with an evidence-based verdict and the published compare-page link.search_agents: search the HVTracker registry by name, repo, description, or category.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?
Related MCP server: Agent Identity MCP Server
Check your AI dependencies in CI
HVTrust Gate runs the same trust checks in
GitHub Actions. With no configuration it reads your requirements.txt, pyproject.toml,
package.json and MCP client configs, and comments on pull requests that change them with
the HVTrust grade of each AI agent and MCP server you depend on.
name: HVTrust
on: [pull_request]
permissions:
contents: read
pull-requests: write
jobs:
trust:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v7
- uses: YugantM/hvtrust-gate@v1Local Install
With npm:
npm install -g hvtracker-mcpWith PyPI:
python3 -m pip install hvtracker-mcpExample MCP client config:
{
"mcpServers": {
"hvtracker": {
"command": "hvtracker-mcp"
}
}
}Development
python3 -m pip install -e ".[dev]"
python3 -m pytest
hvtracker-mcpUse a different HVTracker base URL while testing:
HVTRACKER_BASE_URL=http://localhost:8080 hvtracker-mcpRegistry Publishing
The official MCP Registry manifest is server.json.
mcp-publisher login github
mcp-publisher publishIn GitHub Actions, run the "Publish MCP Registry" workflow after the npm, PyPI, and GHCR packages for the same version are live.
The server name is:
io.github.YugantM/hvtracker-mcpClaude Desktop Extension
Tagged releases build an .mcpb bundle for Claude Desktop from manifest.json.
To build it locally:
npm ci --omit=dev
npx @anthropic-ai/mcpb@2.1.2 packPrivacy
HVTracker MCP sends the user-supplied search string or server identifier to
https://hvtracker.net to fetch public trust data. It does not require an API
key and does not write to user systems. See the HVTracker site for current data
and methodology, and see PRIVACY.md for the repository privacy note.
Available Tools
8 toolscheck_agent_trustCheck Agent TrustBRead-onlyIdempotentInspect
Get the HVTracker trust profile for a tracked AI agent or framework, including its runtime capability surface and the URL of its Ed25519-signed trust credential (verifiable offline).
Inputs: name_or_repo (required). Returns: object
compare_agentsCompare AgentsARead-onlyIdempotentInspect
Compare two tracked AI agents side by side: both trust profiles, an evidence-based one-line verdict, and the HVTracker compare-page URL when one is published.
Inputs: a (required), b (required). Returns: object
get_agent_historyGet Agent HistoryARead-onlyIdempotentInspect
90-day trust-score, grade, and rank history for one tracked agent — is it improving or declining? Accepts the same identifiers as check_agent_trust.
Inputs: name_or_repo (required). Returns: object
get_leaderboardGet LeaderboardARead-onlyIdempotentInspect
Top tracked AI agents and MCP servers by HVTrust score, optionally scoped to one category (exact name from list_categories).
Inputs: limit, category. Returns: object
list_categoriesList CategoriesARead-onlyIdempotentInspect
List HVTracker categories with agent counts (most-populated first), so you can then pull a category's leaderboard.
Inputs: no named parameters. Returns: object
scan_stackScan StackARead-onlyIdempotentInspect
Bulk pre-connect trust check for a whole dependency set. Paste a requirements.txt, package.json, MCP client config, or a newline/comma list; each item is returned with a trust verdict plus a stack summary.
Inputs: input (required). Returns: object
search_agentsSearch AgentsARead-onlyIdempotentInspect
Search tracked AI agents and frameworks by name, repo, or description.
Inputs: limit, query, category. Returns: object
verify_mcp_serverVerify MCP ServerARead-onlyIdempotentInspect
Pre-connect trust verdict for an MCP server or AI agent.
Pass a GitHub owner/repo, GitHub URL, npm/PyPI package, display name, slug, or MCP server URL. Unknown servers return trusted=false because HVTracker has no independent evidence, not because harm is proven.
Inputs: server (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Most tools have distinct purposes, but check_agent_trust and verify_mcp_server both provide trust verdicts for agents/servers, potentially causing confusion. Descriptions help differentiate, but overlap remains.
All tool names consistently follow a verb_noun pattern in snake_case, such as check_agent_trust, compare_agents, and list_categories.
With 8 tools, the server covers core querying needs without being cluttered. Each tool serves a clear function, and the count feels appropriate for a trust tracker.
The set covers trust checks, comparison, history, leaderboard, categories, bulk scanning, search, and MCP verification. Minor gaps exist, such as no individual category detail tool, but overall coverage is solid.
Maintenance
Related MCP Connectors
The MCP server that vets MCP servers: identity, risk grade and per-tool risk before you install.
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
Search, vet & assemble MCP servers from your agent: verified tools, risk labels, and trust scores.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Related MCP Servers
- AlicenseAqualityDmaintenanceMCP server for AI agent identity — verify agents with Ed25519 signatures, check trust scores, sign and verify content, exchange encrypted messages. Built on the Agent Identity Protocol (AIP).81MIT
- AlicenseNot gradedqualityDmaintenanceMCP Server for AI agent identity and authorization. Create, verify, and manage agent identities with trust scores and scoped authorization tokens.48 PyPIMIT
- AlicenseNot gradedqualityDmaintenanceMCP server for Citizen of the Cloud — agent identity verification, trust scoring, and registry access for any AI runtime that speaks the Model Context Protocol.22 npmMIT
- AlicenseAqualityDmaintenanceMCP server for AI agent trust verification, enabling agents to verify identities, check trust scores, and build reputation across multiple blockchain and web platforms.1220 npm1MIT