MadTaco runs on your own machine — the client starts it, so there is no endpoint to ping. 79 installs a week from npm. Last commit 11 Jul 2026.
Verification and trust checks for AI agents: validate, screen, propose, accounts, usage.
Today is the operative word: we check MadTaco 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 mcp -- npx -y @madtaco/mcp
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@madtaco/mcp"
]
}
}
}
[mcp_servers.mcp]
command = "npx"
args = ["-y", "@madtaco/mcp"]
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@madtaco/mcp"
]
}
}
}
{
"servers": {
"mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@madtaco/mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
MADTACO_API_BASE (MadTaco API base URL (default: https://api.madtaco.dev/v1)), MADTACO_API_KEY (X-Api-Key for paid checks, usage, and proposals (free tools work without it)).
Verification and research desk for agents: packet validation, token screens, settlement checks.
On-chain trust verification and Street Cred for AI agents. ERC-8004, multi-chain.
Merchant trust verification for AI agents. One call = trust score, badge, and purchase safety.
Universal trust attestation for AI agents: create, verify, and negotiate Shuka trust proofs.
Verify a proposed action against a signed Agent Mandate without executing or mutating accounts.
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
Security scanning and trust verification for AI agent tools.
Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.
Answers built from our own checks of this server.