🌮 MadTaco MCP — verification and trust checks for AI agents.
Description
Validate tax IDs, IBANs, emails, and phones. Screen entities against sanctions lists (OFAC, EU, UK, UN). Verify companies, inspect domains, and run composite trust screens. Create accounts, check usage, and propose new capabilities. Free tools (tax-id, IBAN, email syntax, phone format, Chilean indicators) work without an API key. Paid checks need a funded MadTaco account — authenticate with your API key via X-Api-Key. Every response includes credits_charged; failed checks are never billed. Setup: madtaco.dev/mcp API docs: madtaco.dev/docs Pricing: madtaco.dev/pricing.json
What our measurements say
🌮 MadTaco MCP — verification and trust checks for AI agents. is a remote MCP server published at api.madtaco.dev. It has been probed 7 times since 9/10/2026. It answered in 7 of them (100.0%), a near-uninterrupted record. Median response time is 1,222 ms, a delay an agent will notice. It exposes a broad tool surface of 15 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Agent readability score
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
Agent readability score
Strengths
- Most tool names clearly indicate their purpose (e.g., 'validate_tax_id', 'screen_sanctions').
- Descriptions include cost tiers and API key requirements for paid tools.
- Composite tools like 'screen' consolidate multiple checks efficiently.
Weaknesses
- Tool 'screen' has a generic name that doesn't specify its composite nature.
- Some descriptions lack context for when to use the tool (e.g., 'lookup_instrument').
- Overlap between composite ('screen') and individual tools may confuse agents.
screen— Name is too generic; doesn't clarify it's a composite trust check.lookup_instrument— Description doesn't explain use cases (e.g., financial instruments).screen_sanctions— No mention of response format or error handling details.
Verdict
Event narrative
Risk: medium
- 2026-09-10T21:16:35.016Z — Era changed from auth-gated to legacy · Indicates system moved to a trusted state with full compliance verification
- 2026-09-11T03:50:39.090Z — Compliance score increased from null to 100 · Confirms full regulatory compliance achieved in legacy era
Advice
Schema compliance
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
- tools/list schema valid
- inputSchema is valid JSON Schema
- Smoke test not run this round
- Cold-start: cold 185ms → warm 167ms (penalty 18ms)
Availability history
Event log
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
- Server build: — → 1.2.0
- Supported versions: — → 2025-11-25
- Era changed: Auth-gated → Legacy
- Added to watch — era: Auth-gated
Get your badge
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/madtaco-madtaco-mcp)<a href="https://mcpmetrics.io/servers/madtaco-madtaco-mcp"><img src="https://mcpmetrics.io/badge/madtaco/madtaco-mcp/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to see