Trust Engine/MCP Server

STiFLeR7/memex

Persistent memory for AI coding agents via MCP — a bitemporal knowledge graph of your codebase, served to Claude Code, Cursor, Gemini CLI, and any MCP client. Tree-sitter + Gemini Flash → Neo4j (via Graphiti). 12 MCP tools, hierarchical clusters, two-regime confidence decay.

11 starsPythonMITclaude-codecodexgemini-climcp
REVIEWED85/100

Scanned 2026-06-22 · deepseek v1

Dimension breakdown

Security

72/100

6 findings

Quality

85/100

No findings

License

95/100

No findings

Completeness

92/100

No findings

Findings (6)

MEDIUM: 3LOW: 2INFO: 1
  • MEDIUMsecurityDefault credentials documented in README
  • MEDIUMsecurityHTTP transport uses bearer token without TLS enforcement
  • MEDIUMsecurityPotential Cypher injection in cluster graph queries
  • LOWsecurityGemini API key exposed in environment variable example
  • LOWsecurityNo input validation on module paths in cluster functions

Detailed file:line citations + recommended fixes are visible to the maintainer of this repo after claiming the listing.

Maintainer of this repo?

Claim this listing in 30 seconds with GitHub OAuth. You'll see detailed findings, get notified about matched bounties, and can trigger re-scans on demand.

Claim listing

Embed the badge.

Drop it into your README. Every view backlinks to this verification page.

Trust badge — flat styleTrust badge — for-the-badge style

Markdown

[![Archimedes Trust](https://archimedes.market/api/badge/STiFLeR7/memex.svg)](https://archimedes.market/r/STiFLeR7/memex)

HTML

<a href="https://archimedes.market/r/STiFLeR7/memex"><img src="https://archimedes.market/api/badge/STiFLeR7/memex.svg" alt="Archimedes Trust Verified"/></a>