MadTaco MCP server
dev.madtaco/mcp·v1.1.0Verification and trust checks for AI agents: validate, screen, propose, accounts, usage.
0 stars60 downloads/wk
Reviews
Write oneNobody has reviewed MadTaco yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
MadTaco tools (12, 3 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
create_accountwrite actionCreate a MadTaco account (agent-native signup). A 6-digit verification code is emailed — no API key yet.
get_usageGet today usage totals, per-operation counts, credits spent, and balance. Optional period=7d|30d for daily breakdown.
inspect_domainInspect domain age, DNS posture, and lookalike risk. Costs 0.05 credits (tier 2).
propose_checkPropose a new check capability MadTaco does not offer yet. Optionally pledge credits (held, not charged).
screenwrite actionRun a composite trust screen across sanctions, registry, domain, email, and phone checks. Only completed checks are charged. Optionally long-polls when still running.
screen_sanctionsScreen a name against OFAC SDN, EU, UK, and UN sanctions lists. Costs 0.10 credits (tier 2).
validate_emailwrite actionValidate an email address. mode "syntax" is free; mode "full" costs 0.005 credits (tier 2).
validate_ibanValidate an IBAN checksum and parse country and bank code. Free — no API key required.
validate_phoneValidate a phone number. mode "format" is free; mode "full" costs 0.005 credits (tier 2).
validate_tax_idValidate a tax ID format and checksum. Supports CL RUT, MX RFC, and more. Free — no API key required.
verify_accountVerify the emailed 6-digit code and receive an API key (tier registered).
verify_companyVerify a company against an official registry (GB only in v1). Costs 0.15 credits (tier 2).
Public scan report
scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it
- Code scan9 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 76 days ago12/15
- Maintainer identitynamespace and repository owner differ; website matches verified namespace6/10
How MadTaco compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 75/100
- higher than 45% of 48,255 servers
- Tools
- 12
- the typical server has 7
- Tools that change things
- 25%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 60
- more than 49% of 12,191 servers with a package
What its tools let an agent do: 9 read · 1 create · 2 change
Install MadTaco in Claude Code, Cursor or VS Code
Runs npx -y @madtaco/mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add mcp -- npx -y @madtaco/mcp
What the publisher says
From the MadTaco repository's README, as published. We do not edit it. Read it on GitHub
🌮 MadTaco — MCP Server
npm: @madtaco/mcp
Verification and utility API for AI agents. Validate tax IDs, screen sanctions, verify companies, inspect domains — prepaid USD credits. Failed checks are never charged.
This package is a stdio MCP server that wraps the public MadTaco API at https://api.madtaco.dev/v1. Every response includes credits_charged (0 for free operations). Prefer remote HTTP instead? See HTTP MCP below.
Docs
- madtaco.dev — product site
- Setup guide — Cursor, Claude, Smithery
- API docs — OpenAPI reference
- Agent skill — integration guide (MCP + REST)
- llms.txt — full endpoint catalog
- pricing.json — per-operation prices
- Health — API status
- Server card — tool metadata
Quick start (stdio)
npx @madtaco/mcpClaude Desktop / Cursor
Claude Desktop config: ~/Library/Application Support/Claude/claudedesktopconfig.json (macOS) or %APPDATA%\Claude\claudedesktopconfig.json (Windows). Cursor: .cursor/mcp.json in your project or global MCP settings.
{
"mcpServers": {
"madtaco": {
"command": "npx",
"args": ["-y", "@madtaco/mcp"],
"env": {
"MADTACO_API_KEY": "your_api_key_here"
}
}
}
}Without an API key: validatetaxid, validateiban, lookupinstrument, validateemail (syntax), validatephone (format), createaccount, verifyaccount.
With an API key (tier registered): getusage, proposecheck.
Funded account required (tier 2): paid screening/verification tools and validateemail/validatephone full modes. Top up via POST /v1/billing/checkout or madtaco.dev billing.
Rate limits: 50 req/day anonymous (per IP), 100 req/day registered (per API key), 500/day included once funded — see llms.txt.
Try it
Validate the Chilean RUT 11.111.111-1 using MadTaco.
Check whether IBAN DE89370400440532013000 is valid.
Look up ticker CMG on exchange US.
Remote HTTP
Streamable HTTP MCP on the API subdomain — no npm install required:
{
"mcpServers": {
"madtaco": {
"url": "https://api.madtaco.dev/mcp",
"headers": { "X-Api-Key": "your_api_key_here" }
}
}
}Authenticate with X-Api-Key or Authorization: Bearer. Same 13 tools as this stdio package.
Environment
Override for staging or local dev:
"env": { "MADTACO_API_BASE": "https://api.madtaco.dev/v1" }Tools
All paths are relative to MADTACOAPIBASE (default https://api.madtaco.dev/v1).
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
MadTaco: common questions
- Is MadTaco MCP server safe?
- Mostly: it is graded B (75/100). Read the MadTaco safety report
- How do I install MadTaco?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does MadTaco need an API key?
- Yes. The registry entry asks for
MADTACO_API_KEY. - Is MadTaco maintained?
- The last commit was 116 days ago (2026-07-11). The latest release is v1.1.0.
- How does MadTaco compare with other MCP servers?
- safety score 75/100 (higher than 45% of 48,255 servers); tools 12 (the typical server has 7); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.