WhiteMagic — governed local memory for agent continuity
io.github.lbailey94/whitemagic-mcp · v11.2.1 · score 81/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Governed local-first memory and continuity for AI agents — signed receipts, optional hosted lane.
Source: https://github.com/lbailey94/whitemagic
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 59 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (service.request_eval_key). Require confirmation before the agent calls them. |
| Medium | MW002 | Package docker.io/lbailey94/whitemagic:11.2.1 is published without a fixed version. |
What was checked
- https://mcp.whitemagic.dev/mcp: answers without auth
- npm: whitemagic-mcp@11.2.1 (static checks only; code not executed)
- oci: docker.io/lbailey94/whitemagic:11.2.1@? (static checks only; code not executed)
Public tools: wm, memory.create, memory.search, memory.temporal_query, memory.read, memory.list, memory.hybrid_recall, galaxy.list, galaxy.fork, galaxy.create, session.record, session.continuity, session.start, memory.update, memory.revisions, session.checkpoint, memory.ingest, receipts.emit, receipts.verify, memory.count, memory.stats, memory.tags, memory.aggregate, memory.associations, memory.batch_read, memory.query, memory.filter, memory.pin, memory.search_batch, session.list
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-lbailey94-whitemagic-mcp-6287747c)