MCP-native shared memory for Claude Code agents — hybrid BM25+vector+RRF recall, cross-session continuity, cognitive scoring, knowledge graph. Self-hosted, $0/query. 30 MCP tools.
- capability exposure inferred + 35
- recent drift inferred + 12
- tool safety inferred + 12
- trust mitigators mixed − 3
inferred mixed
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 →
- B · 34 → C · 56
- C · 46 → B · 34
- C · 54 → C · 46
- C · 59 → C · 54
- C · 51 → C · 59
- A · 13 → C · 51
No known CVEs for this server.
- high dangerous code
committed secret: Anthropic key
- medium dangerous code
env-secret-flows-to-network-py: An environment value (often a secret/token) flows into a network call — possible credential exfiltration. (gregdigittal-depthfusion-dbb81c7/src/dept
analyzed commit dbb81c7 · analyzer v28 · 3h ago
skills & prompt files 16
- agent-rules gregdigittal-depthfusion-dbb81c7/AGENTS.md
- agent-rules gregdigittal-depthfusion-dbb81c7/CLAUDE.md
- agent-rules gregdigittal-depthfusion-dbb81c7/docs/Account_synch/AGENTS.md
- agent-rules gregdigittal-depthfusion-dbb81c7/docs/Account_synch/CLAUDE.md
- skill gregdigittal-depthfusion-dbb81c7/docs/designs/DepthFusion Design System/SKILL.md
- prompt-file gregdigittal-depthfusion-dbb81c7/docs/designs/DepthFusion Design System/components/brand/LogoMark.prompt.md
- prompt-file gregdigittal-depthfusion-dbb81c7/docs/designs/DepthFusion Design System/components/core/Avatar.prompt.md
- prompt-file gregdigittal-depthfusion-dbb81c7/docs/designs/DepthFusion Design System/components/core/Badge.prompt.md
- prompt-file gregdigittal-depthfusion-dbb81c7/docs/designs/DepthFusion Design System/components/core/Button.prompt.md
- prompt-file gregdigittal-depthfusion-dbb81c7/docs/designs/DepthFusion Design System/components/core/Card.prompt.md
- prompt-file gregdigittal-depthfusion-dbb81c7/docs/designs/DepthFusion Design System/components/data/NodeChip.prompt.md
- prompt-file gregdigittal-depthfusion-dbb81c7/docs/designs/DepthFusion Design System/components/data/ResultCard.prompt.md
- prompt-file gregdigittal-depthfusion-dbb81c7/docs/designs/DepthFusion Design System/components/forms/Checkbox.prompt.md
- prompt-file gregdigittal-depthfusion-dbb81c7/docs/designs/DepthFusion Design System/components/forms/Input.prompt.md
- prompt-file gregdigittal-depthfusion-dbb81c7/docs/designs/DepthFusion Design System/components/forms/Radio.prompt.md
- prompt-file gregdigittal-depthfusion-dbb81c7/docs/designs/DepthFusion Design System/components/navigation/Tabs.prompt.md
danger signals2
- committed secret Anthropic key gregdigittal-depthfusion-dbb81c7/tests/test_install/test_install.py :382
sk-ant…(31 chars, redacted) - committed secret Anthropic key gregdigittal-depthfusion-dbb81c7/tests/test_scripts/test_mine_session_prompts.py :84
sk-ant…(45 chars, redacted)
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:gregdigittal/depthfusion/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 gregdigittal.