⚠️ This snapshot is over 30 days old — treat the grade as stale until the next refresh. Re-scan locally to verify.
Trust Card · Static snapshot
mcp-memory D
54/100 · 5 findings (0 critical) · scope broad · Ranked #38 of 53 scanned.
Scanned 2026-09-09 · engine v0.1.0 (8 regex rules, OWASP-mapped) · upstream modelcontextprotocol/servers @ d73f99e (2026-09-02)
Score breakdown
Score constrained by 0 critical and 5 high-severity findings.
Fix first (5 critical/high)
| Severity | Rule | Finding | Remediation |
|---|---|---|---|
| HIGH | AT-SEC-005 (ASI02) | Unrestricted Recursive File Deletion / Modification__tests__/delete-reporting.test.ts:35Evidence: await fs.unlink(testFilePath); | Enforce strict jail/root directories and require explicit human-in-the-loop confirmation before file deletions. |
| HIGH | AT-SEC-005 (ASI02) | Unrestricted Recursive File Deletion / Modification__tests__/file-path.test.ts:32Evidence: await fs.unlink(oldMemoryPath); | Enforce strict jail/root directories and require explicit human-in-the-loop confirmation before file deletions. |
| HIGH | AT-SEC-005 (ASI02) | Unrestricted Recursive File Deletion / Modification__tests__/file-path.test.ts:37Evidence: await fs.unlink(newMemoryPath); | Enforce strict jail/root directories and require explicit human-in-the-loop confirmation before file deletions. |
| HIGH | AT-SEC-005 (ASI02) | Unrestricted Recursive File Deletion / Modification__tests__/knowledge-graph.test.ts:23Evidence: await fs.unlink(testFilePath); | Enforce strict jail/root directories and require explicit human-in-the-loop confirmation before file deletions. |
| HIGH | AT-SEC-005 (ASI02) | Unrestricted Recursive File Deletion / Modificationindex.ts:197Evidence: await fs.unlink(tempFilePath).catch(() => {}); | Enforce strict jail/root directories and require explicit human-in-the-loop confirmation before file deletions. |
Permissions
Scope: broad · Shell: disabled · Network egress: no · File deletion: enabled · Human approval: none
Provenance
License: SEE LICENSE IN LICENSE · Lockfile: no · Security policy: no · Signals: unverified origin
Independently scanned by the AgentTrust registry (not self-reported by the project). Static analysis only — no code executed, findings need human triage, counts may include test/example code. Static snapshot; re-scan before relying on it: npx @eulogik/agenttrust scan https://github.com/modelcontextprotocol/servers/tree/main/src/memory. Scores move with every upstream commit; pages refresh weekly. How scoring works.