@cachly-dev/mcp-server@0.10.125
Your AI forgets everything between sessions. cachly fixes that permanently: 122 MCP tools for Claude Code, Cursor, Copilot & Windsurf. Learns from every bug fix, commit and CI run. Arrives pre-briefed. Free tier forever, EU servers, GDPR.
AI Security Review
scanned 2mo ago · by lpm-firewall-aiSource inspection found a risky but explicit first-party AI-agent extension workflow, not concrete malicious installation behavior or covert credential exfiltration. The postinstall script is informational only.
Decision evidence
public snapshot- Explicit setup/autopilot writes MCP config, including global Claude config with a Cachly credential.
- Setup installs Claude lifecycle hooks that process prompt/tool events.
- The user-invoked index_project tool reads project files and submits excerpts to a vector endpoint.
- postinstall only prints onboarding text; it does not mutate files or start network activity.
- Config and hook writes are gated behind explicit CLI setup/autopilot, not npm installation.
- Default API endpoint is Cachly-owned; no unrelated credential-harvesting or covert payload path was found.
Source & flagged code
14 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 unpkgPackage source references child process execution.
dist/src/bench/cachly-bench.jsView on unpkg · L40Findings
Affected versions and remediation
This report applies to @cachly-dev/mcp-server@0.10.125.
See all versions of @cachly-dev/mcp-server for other recorded verdicts.
- Review the evidence and your use of @cachly-dev/mcp-server@0.10.125 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.