Adaptive memory for AI agents & teams — beyond RAG. Self-hosted MCP server that gets smarter every time you search: hybrid search + a neural memory graph that learns. Works with Claude, ChatGPT & any MCP client.
- capability exposureinferred+35
- tool safetyinferred+25
- trust mitigatorsmixed−3
inferredmixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 7m ago · see ecosystem CVEs →
No known CVEs for this server.
- highdangerous code
env-secret-flows-to-network-py: An environment value (often a secret/token) flows into a network call — possible credential exfiltration. (/tmp/obs-code-MrbLsc/kagura-ai-memory-clo
- highexfiltration comboinit_file_upload
single tool reads + sends: fs, net
- highexfiltration combocomplete_file_upload
single tool reads + sends: fs, net
- highexfiltration comboget_file_download_url
single tool reads + sends: fs, net
- hightoxic flow (lethal trifecta)get_file_download_url
single tool reads private data, ingests untrusted content, and reaches the network: fs, net
- mediumtool shadowingdelete_file
tool "delete_file" shadows a verified server's tool
analyzed commit 5be4a1d · analyzer v17 · 3d ago
skills & prompt files 3
[](https://mcpobservatory.com/servers/github:kagura-ai/memory-cloud/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of kagura-ai.