
Security News
Re-Enabled GitHub Actions Expose Thousands of Repositories to Mini Shai-Hulud
Two compromised GitHub Actions were re-enabled with malicious tags intact, exposing thousands of downstream repositories to Mini Shai-Hulud.
reference-mcp
Advanced tools
Reference integrity for AI agents. Scans a repository for URLs, imports, assets, and dependencies, then verifies each reference resolves.
Reference integrity for AI agents. Scans a repository for every reference, URLs, imports, assets, and dependencies, then verifies each one resolves. Catches the dead link, the missing import, and the removed package before an agent acts on them.
Built as an MCP server, so it works in any platform that speaks Model Context Protocol.
Agents assume references resolve. They import a file that was renamed, link a repo that was deleted, or depend on a package that was unpublished, and only discover it after wasting a session. Reference finds the broken references up front.
reference.scan extract every reference from a repository, deduplicated by kindreference.check verify local paths against the filesystem, module names against the npm registry, and URLs over HTTP. Returns findings with a status per reference and a BROKEN_REFERENCES or ALL_OK verdict.Reference kinds: local relative imports, module npm dependencies, url web links, asset images and static files.
npm install -g reference-mcp
{
"mcpServers": {
"reference": {
"command": "reference-mcp",
"args": []
}
}
}
MIT. Part of the Tawakkul Labs MCP family.
Links: npm | GitHub | Tawakkul Labs
FAQs
Reference integrity for AI agents. Scans a repository for URLs, imports, assets, and dependencies, then verifies each reference resolves.
The npm package reference-mcp receives a total of 100 weekly downloads. As such, reference-mcp popularity was classified as not popular.
We found that reference-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
Two compromised GitHub Actions were re-enabled with malicious tags intact, exposing thousands of downstream repositories to Mini Shai-Hulud.

Research
/Security News
A malicious Firefox extension fetches its payload after installation to evade detection, steal Google session cookies, and automate account takeover.

Research
/Security News
The compromise affects MemTensor's MemOS, an open source memory framework for large language models (LLMs) and AI agents. Both npm package @memtensor/memos-cloud-openclaw-plugin and the PyPI package MemoryOS are compromised. They drop cross-platform Go binaries that exfiltrate developer secrets.