Pre-connect trust checks for AI agents and MCP servers using HVTracker's public trust registry.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Get the HVTracker supply-chain trust profile for a tracked AI agent or framework.
Get the HVTracker supply-chain trust profile for a tracked AI agent or framework.
| Argument | Type | Description |
|---|---|---|
| name_or_repo* | string |
{
"type": "object",
"title": "check_agent_trustArguments",
"required": [
"name_or_repo"
],
"properties": {
"name_or_repo": {
"type": "string",
"title": "Name Or Repo"
}
}
}Compare two tracked AI agents side by side: trust scores, grades, runtime capabilities, and an evidence-based verdict.
| Argument | Type | Description |
|---|---|---|
| a* | string | |
| b* | string |
{
"type": "object",
"title": "compare_agentsArguments",
"required": [
"a",
"b"
],
"properties": {
"a": {
"type": "string",
"title": "A"
},
"b": {
"type": "string",
"title": "B"
}
}
}90-day trust-score, grade, and rank history for one tracked agent — is it improving or declining?
| Argument | Type | Description |
|---|---|---|
| name_or_repo* | string |
{
"type": "object",
"title": "get_agent_historyArguments",
"required": [
"name_or_repo"
],
"properties": {
"name_or_repo": {
"type": "string",
"title": "Name Or Repo"
}
}
}Top tracked AI agents and MCP servers ranked by HVTrust score, optionally filtered to one category.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| category | string |
{
"type": "object",
"title": "get_leaderboardArguments",
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 10
},
"category": {
"type": "string",
"title": "Category",
"default": ""
}
}
}List the HVTracker categories with agent counts, so you can then pull a category's leaderboard.
No arguments.
{
"type": "object",
"title": "list_categoriesArguments",
"properties": {}
}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.
| Argument | Type | Description |
|---|---|---|
| input* | string |
{
"type": "object",
"title": "scan_stackArguments",
"required": [
"input"
],
"properties": {
"input": {
"type": "string",
"title": "Input"
}
}
}Search tracked AI agents and frameworks by name, repo, description, or category, ranked by trust score.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| query | string | |
| category | string |
{
"type": "object",
"title": "search_agentsArguments",
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 10
},
"query": {
"type": "string",
"title": "Query",
"default": ""
},
"category": {
"type": "string",
"title": "Category",
"default": ""
}
}
}Pre-connect trust verdict for an MCP server, package, GitHub repo, or agent name before connecting an AI agent to it.
| Argument | Type | Description |
|---|---|---|
| server* | string |
{
"type": "object",
"title": "verify_mcp_serverArguments",
"required": [
"server"
],
"properties": {
"server": {
"type": "string",
"title": "Server"
}
}
}