
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.
@mdtidy/mcp
Advanced tools
Model Context Protocol server for Markdown Tidy (mdtidy.com) — tidy, convert, save, and share Markdown from any AI agent.
Model Context Protocol server for mdtidy.com — clean, convert, save, and share Markdown from any AI agent.
Create an API key at https://mdtidy.com/account/api-keys, then:
# Claude Code
claude mcp add mdtidy --env MDTIDY_API_KEY=mt_live_… -- npx -y @mdtidy/mcp
// Any stdio client (.mcp.json / client MCP config)
{
"mcpServers": {
"mdtidy": {
"command": "npx",
"args": ["-y", "@mdtidy/mcp"],
"env": { "MDTIDY_API_KEY": "${MDTIDY_API_KEY}" }
}
}
}
Or point any client at the hosted https://mdtidy.com/mcp with
Authorization: Bearer mt_live_….
mdtidy-mcp (bin) — stdio server. Reads MDTIDY_API_KEY (and optional
MDTIDY_BASE_URL).@mdtidy/mcp/http — createMcpRouteHandler(), the stateless Streamable-HTTP
handler the mdtidy /mcp route mounts.@mdtidy/mcp — library exports (registerTools, REGISTRY, createMdtidyClient, …).Full tool reference: https://github.com/mdtidy/mdtidy-agents/blob/main/docs/tools.md.
MIT.
FAQs
Model Context Protocol server for Markdown Tidy (mdtidy.com) — tidy, convert, save, and share Markdown from any AI agent.
The npm package @mdtidy/mcp receives a total of 42 weekly downloads. As such, @mdtidy/mcp popularity was classified as not popular.
We found that @mdtidy/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.