Veragent runs on your own machine — the client starts it, so there is no endpoint to ping. 61 installs a week from pypi. Last commit 24 Jun 2026.
Check the trust/security score of MCP servers, agents, skills & CLIs before you install them.
Today is the operative word: we check Veragent every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add veragent -- uvx veragent-mcp
{
"mcpServers": {
"veragent": {
"args": [
"veragent-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.veragent]
command = "uvx"
args = ["veragent-mcp"]
{
"mcpServers": {
"veragent": {
"args": [
"veragent-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"veragent": {
"args": [
"veragent-mcp"
],
"command": "uvx"
}
}
}
MCP security trust-check for agents before installing MCPs, Skills or tools.
Security grades (A-F) for MCP servers. Check one before you install or trust it. mcpgrade.dev
Search and install 20,000+ security-graded MCP servers and agent skills.
Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.
Trust verification for MCP servers. Check scores, scan for security issues, search 4,200+ servers.
Free, read-only security scanner for remote MCP servers, before you connect them.
Security scanner for AI agent skills and MCP servers
Inspect an MCP server for common security risks before you install it. Offline, zero telemetry.
Answers built from our own checks of this server.