@cachly-dev/mcp-server@0.10.200
Solve it once. From then on, your AI knows. Experience for coding agents, EU-hosted: an MCP server for Claude Code, Cursor, Copilot & Windsurf. Learns from every bug fix, commit and CI run.
AI Security Review
scanned 8d ago · by lpm-firewall-aiThe source confirms default automatic indexing that can transmit project excerpts to the package's Cachly service without a separate indexing request. The service is aligned with the package's coding-memory purpose and the behavior has an opt-out, so this warrants a warning rather than a block.
Decision evidence
public snapshot- dist/src/index.js starts project indexing automatically during an MCP session, up to 150 files, unless CACHLY_AUTO_INDEX is set to false; it repeats after a day.
- dist/src/handlers/cache.js reads file contents and creates a path plus excerpt for each indexed file.
- When semantic indexing is available, the handler posts that excerpt to the configured Cachly semantic endpoint.
- The package identifies itself as a coding memory service, and the destination is its Cachly service; this supports product alignment but does not establish affirmative consent to automatic indexing.
- The indexing trigger has an explicit opt-out, and source inspection shows transfer to the package-aligned Cachly service rather than an unrelated recipient.
Source & flagged code
19 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgFindings
Affected versions and remediation
This report applies to @cachly-dev/mcp-server@0.10.200.
See all versions of @cachly-dev/mcp-server for other recorded verdicts.
- Review the evidence and your use of @cachly-dev/mcp-server@0.10.200 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.