MadTaco
NPM · @MADTACO/MCP · SCANNED SEP 22
Verification and trust checks for AI agents: validate, screen, propose, accounts, usage.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 72 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability76
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 861 tokens (~71/item across 12 items; 12 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage97
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 90% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the MadTaco MCP server?
MadTaco runs locally as an npm package, launched with npx -y @madtaco/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @madtaco/mcp
claude mcp add dev-madtaco-mcp -- npx -y @madtaco/mcp
{
"mcpServers": {
"dev-madtaco-mcp": {
"command": "npx",
"args": [
"-y",
"@madtaco/mcp"
]
}
}
} {
"servers": {
"dev-madtaco-mcp": {
"command": "npx",
"args": [
"-y",
"@madtaco/mcp"
]
}
}
} codex mcp add dev-madtaco-mcp -- npx -y @madtaco/mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"dev-madtaco-mcp": {
"type": "local",
"command": [
"npx",
"-y",
"@madtaco/mcp"
],
"enabled": true
}
}
} openclaw mcp add dev-madtaco-mcp --command npx --arg -y --arg @madtaco/mcp
mcp_servers:
dev-madtaco-mcp:
command: "npx"
args: ["-y", "@madtaco/mcp"] {
"McpServers": {
"dev-madtaco-mcp": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@madtaco/mcp"
]
}
}
} assistant mcp add dev-madtaco-mcp -t stdio -c npx -a -y @madtaco/mcp
{
"mcpServers": {
"dev-madtaco-mcp": {
"command": "npx",
"args": [
"-y",
"@madtaco/mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 22 Sept 26 +1
- Stability: 0.97 → pass security
- 20 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Sept 26 −3
- Stability: pass → 0.80 functional
- 15 Sept 26 +1
- Stability: 0.97 → pass security
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 9 Sept 26 −3
- Stability: pass → 0.80 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 22 Sept 2026 · Analysed npm/@madtaco/mcp@1.1.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 96 packages
| Packages resolved | 96 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
create_account ~57
Create a MadTaco account (agent-native signup). A 6-digit verification code is emailed — no API key yet.
| Name | Type | Req | Description |
|---|---|---|---|
| string | yes | Account email (disposable domains rejected). | |
| name | string | – | Optional display name. |
No output schema declared.
No examples provided.
get_usage ~54
Get today usage totals, per-operation counts, credits spent, and balance. Optional period=7d|30d for daily breakdown.
| Name | Type | Req | Description |
|---|---|---|---|
| period | string | – | Include daily breakdown for the last 7 or 30 days. |
No output schema declared.
No examples provided.
inspect_domain ~64
Inspect domain age, DNS posture, and lookalike risk. Costs 0.05 credits (tier 2).
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | yes | Domain to inspect, e.g. example.com. |
| idempotency_key | string | – | Optional Idempotency-Key header. |
No output schema declared.
No examples provided.
propose_check ~75
Propose a new check capability MadTaco does not offer yet. Optionally pledge credits (held, not charged).
| Name | Type | Req | Description |
|---|---|---|---|
| capability | string | yes | Description of the capability you want. |
| expected_monthly_volume | integer | – | – |
| pledge_credits | number | – | – |
| willing_to_pay_per_call | number | – | – |
No output schema declared.
No examples provided.
screen ~122
Run a composite trust screen across sanctions, registry, domain, email, and phone checks. Only completed checks are charged. Optionally long-polls when still running.
| Name | Type | Req | Description |
|---|---|---|---|
| checks | array | yes | Checks to run in parallel. |
| entity | object | yes | Entity identifiers — each check uses what it needs. |
| idempotency_key | string | – | Optional Idempotency-Key header. |
| max_credits | number | – | Hard spend cap; excess checks are skipped. |
| wait_seconds | integer | – | Long-poll up to N seconds when status is queued/running. |
No output schema declared.
No examples provided.
screen_sanctions ~93
Screen a name against OFAC SDN, EU, UK, and UN sanctions lists. Costs 0.10 credits (tier 2).
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | – | Optional ISO country hint. |
| idempotency_key | string | – | Optional Idempotency-Key header. |
| match_threshold | number | – | Similarity threshold, default 0.85. |
| name | string | yes | Name to screen. |
No output schema declared.
No examples provided.
validate_email ~61
Validate an email address. mode "syntax" is free; mode "full" costs 0.005 credits (tier 2).
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | Email address to validate. |
| mode | string | – | syntax (free) or full (paid). |
No output schema declared.
No examples provided.
validate_iban ~52
Validate an IBAN checksum and parse country and bank code. Free — no API key required.
| Name | Type | Req | Description |
|---|---|---|---|
| iban | string | yes | IBAN to validate, e.g. "DE89370400440532013000". |
No output schema declared.
No examples provided.
validate_phone ~64
Validate a phone number. mode "format" is free; mode "full" costs 0.005 credits (tier 2).
| Name | Type | Req | Description |
|---|---|---|---|
| mode | string | – | format (free) or full (paid). |
| number | string | yes | Phone number, E.164 preferred. |
No output schema declared.
No examples provided.
validate_tax_id ~82
Validate a tax ID format and checksum. Supports CL RUT, MX RFC, and more. Free — no API key required.
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | yes | ISO 3166-1 alpha-2 country code, e.g. "CL". |
| id | string | yes | Tax ID to validate, e.g. "11.111.111-1". |
No output schema declared.
No examples provided.
verify_account ~51
Verify the emailed 6-digit code and receive an API key (tier registered).
| Name | Type | Req | Description |
|---|---|---|---|
| account_id | string | yes | account_id from create_account. |
| code | string | yes | 6-digit verification code from email. |
No output schema declared.
No examples provided.
verify_company ~86
Verify a company against an official registry (GB only in v1). Costs 0.15 credits (tier 2).
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | yes | ISO 3166-1 alpha-2 country code. |
| idempotency_key | string | – | Optional Idempotency-Key header. |
| name | string | – | Company name. |
| registration_number | string | – | Registry number. |
No output schema declared.
No examples provided.
What is the MadTaco MCP server?
MadTaco is an MCP server listed in the public MCP registry as dev.madtaco/mcp. Verification and trust checks for AI agents: validate, screen, propose, accounts, usage. This page covers its npm package (@madtaco/mcp).
Is the MadTaco MCP server safe to use?
MadTaco scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 22 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the MadTaco MCP server expose?
MadTaco exposes 12 tools: validate_tax_id, validate_iban, validate_email, validate_phone, screen_sanctions, and 7 more. Their descriptions and schemas cost roughly 861 tokens of context every time the server is loaded.
Is the MadTaco MCP server still maintained?
MadTaco is still listed as active in the MCP registry. We last reached this channel on 22 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the MadTaco MCP server under?
MadTaco declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.