Live survey286 models · 13 providers · 17,592 auditsAudited Using Git Worktrees · SAFE →What changedHow we verifyllms.txt

MCP servers · publisher

MCP servers by mnemox-ai

mnemox-ai publishes 3 MCP servers in the atlas. 1 are SAFE, 0 CAUTION and 2 BLOCK. Each was read in full before it was listed.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
CoCopilotAIGoogle AI Mode
Cite

Cite this page

ModelsAtlas. “MCP servers by mnemox-ai”. Retrieved 28 Oct 2026. https://modelsatlas.com/mcp/mnemox-ai

Verdicts · 3 servers

✓SAFE1!CAUTION0✕BLOCK2

Transports

  • stdio, runs locally2
  • Streamable HTTP, remote2
  • SSE, legacy remote0
  • Not declared1

A server can list more than one transport.

3 servers by mnemox-ai

1–3 of 3 · ranked by trust score, then stars

Idea Reality

mnemox-ai/idea-reality-mcp

✓SAFE B

Pre-build reality check for AI coding agents. Scans GitHub, HN, npm, PyPI, Product Hunt. MCP server. 290+ stars.

★ 8221 readstdio

AgentRelay

mnemox-ai/agentrelay

✕BLOCK D

Verifiable microtask protocol for AI agent collaboration. Task lifecycle, validation engine, reputation system.

★ 672 write

TradeMemory

mnemox-ai/tradememory-protocol

✕BLOCK F

Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, tamper-evident SHA-256 chain with RFC 3161 anchoring, 20 MCP tools.

★ 1,4203 writestdio

More from mnemox-ai

mnemox-ai as a publisher →

Questions

Which mnemox-ai MCP server has the best trust score?
Idea Reality (mnemox-ai/idea-reality-mcp) and AgentRelay (mnemox-ai/agentrelay), ranked by trust score and then stars.
Are mnemox-ai's MCP servers read-only?
1 of 3 declare only read tools; 0 expose at least one destructive tool; 0 build their tool list at runtime, so we cannot read it from the source.

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.