A Model Context Protocol (MCP) server for ATLAS, a Neo4j-powered task management system for LLM Agents - implementing a three-tier architecture (Projects, Tasks, Knowledge) to manage complex workflows. Now with Deep Research.
- capability exposure inferred + 4
inferred
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.
grade last moved 6d ago · see ecosystem CVEs →
- B · 22 → A · 4
- B · 27 → B · 22
- B · 15 → B · 27
- A · 10 → B · 15
- A · 12 → A · 10
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed commit 5a0bfdc · analyzer v33 · 3w ago
skills & prompt files 2
- agent-rules cyanheads-atlas-mcp-server-5a0bfdc/.clinerules
- agent-rules cyanheads-atlas-mcp-server-5a0bfdc/CLAUDE.md
danger signals2
- suspicious endpoint analytics.google.com (telemetry) cyanheads-atlas-mcp-server-5a0bfdc/src/mcp/tools/atlas_project_list/index.ts :234
{"title": "Web Vitals Tracking", "url": "https://analytics.google.com/web-vitals"} - suspicious endpoint analytics.google.com (telemetry) cyanheads-atlas-mcp-server-5a0bfdc/src/mcp/tools/atlas_project_update/index.ts :75
url: "https://analytics.google.com/web-vitals",
[](https://mcpobservatory.com/servers/mcpso:cyanheads/atlas-mcp-server/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 cyanheads.