MCP Observatory
npm analyzed 3.0.0-alpha.9 unconfirmed MCP

@claude-flow/neural

v3.0.0-alpha.9
npm

Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear

maintainer
ruvnet
license
MIT
first seen
2026-05-22
last seen
2026-06-16
releases · 30d
8
short id
risk10/100 · heuristic grade
A minimal
  • capability exposureinferred+4
  • inherited (deps)attested+14
  • trust mitigatorsmixed−8

attestedinferredmixed

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 14m ago · see ecosystem CVEs →

risk trajectory2 movements
  • A · 5 → A · 10
  • A · 10 → A · 5
capability exposuregrade factor +4
Inferred surface — each links to servers holding it:
vulnerabilities0 CVEs

no known CVEs for this server.

inherited (deps) · grade factor +14

inherited via dependencies3
HIGH
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse via agentdb · 2 hops CVE-2026-25536 fixed in 1.26.0
HIGH
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability via agentdb · 2 hops CVE-2026-0621 fixed in 1.25.2
HIGH
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default via agentdb · 2 hops CVE-2025-66414 fixed in 1.24.0
tool safetyall quiet

No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.

embed badgereadme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/npm:@claude-flow/neural/badge.svg)](https://mcpobservatory.com/servers/npm:@claude-flow/neural/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 ruvnet.