
Security News
Anthropic Identifies Biased Reasoning and Recklessness as Drivers of Claude’s PyPI Attack
Anthropic found biased reasoning and recklessness drove Claude Mythos 5 to publish malware on PyPI and compromise a security vendor.
@madtaco/mcp
Advanced tools
MadTaco MCP server — verification and trust checks for AI agents.
Talks only to the public MadTaco API (https://api.madtaco.dev/v1). No Laravel dependency; this package is published separately at github.com/madtaco-dev/mcp.
npx @madtaco/mcp
{
"mcpServers": {
"madtaco": {
"command": "npx",
"args": ["-y", "@madtaco/mcp"],
"env": {
"MADTACO_API_KEY": "your_api_key_here"
}
}
}
}
Free tools (validate_tax_id, validate_iban, create_account, verify_account) work without an API key. Paid checks and account tools that read balance/usage require MADTACO_API_KEY.
| Variable | Required | Default |
|---|---|---|
MADTACO_API_KEY | For paid/authenticated tools | — |
MADTACO_API_BASE | No | https://api.madtaco.dev/v1 |
| Tool | API endpoint | Credits |
|---|---|---|
validate_tax_id | POST /validate/tax-id | 0 |
validate_iban | POST /validate/iban | 0 |
validate_email | POST /validate/email | 0 (syntax) / 0.005 (full) |
validate_phone | POST /validate/phone | 0 (format) / 0.005 (full) |
screen_sanctions | POST /screen/sanctions | 0.10 |
verify_company | POST /verify/company | 0.15 |
inspect_domain | POST /inspect/domain | 0.05 |
screen | POST /screen (+ optional long-poll) | sum of completed checks |
propose_check | POST /propose | pledge hold only |
create_account | POST /accounts | 0 |
verify_account | POST /accounts/verify | 0 |
get_usage | GET /usage | 0 |
create_account with an email → account_id + pending_verificationverify_account → api_key (tier registered)POST /v1/billing/checkoutMADTACO_API_KEY and run paid checksCredentials never transit through MCP responses for human dashboard access — use the web invite flow at POST /v1/accounts/invite-human when needed.
cd mcp
npm install
npm test
npm run build
MADTACO_API_KEY=... npm run dev
MIT
FAQs
MadTaco MCP server — verification and trust checks for AI agents
The npm package @madtaco/mcp receives a total of 62 weekly downloads. As such, @madtaco/mcp popularity was classified as not popular.
We found that @madtaco/mcp demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.

Security News
Anthropic found biased reasoning and recklessness drove Claude Mythos 5 to publish malware on PyPI and compromise a security vendor.

Research
/Security News
Malicious Chrome and Firefox extensions target Axiom Trade and Padre users, stealing session tokens and wallet data.

Security News
GPT-6 Astra hits 100% on ExploitBench and finds zero-days autonomously, while independent tests reveal scope violations and monitoring gaps.