An open source implementation of code execution with MCP (Programatic Tool Calling)
- capability exposureinferred+35
- recent driftinferred+12
- tool safetyinferred+12
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.
graded 9m ago · see ecosystem CVEs →
- A · 0 → C · 59
no known CVEs for this server.
- highdangerous code
dynamic exec: __import__()
analyzed commit 425b957 · analyzer v17 · 1d ago
skills & prompt files 5
- skillChen-zexi-open-ptc-agent-425b957/skills/creating-financial-models/SKILL.md
- skillChen-zexi-open-ptc-agent-425b957/skills/docx/SKILL.md
- skillChen-zexi-open-ptc-agent-425b957/skills/pdf/SKILL.md
- skillChen-zexi-open-ptc-agent-425b957/skills/pptx/SKILL.md
- skillChen-zexi-open-ptc-agent-425b957/skills/xlsx/SKILL.md
danger signals1
- dynamic code execution__import__()Chen-zexi-open-ptc-agent-425b957/libs/ptc-agent/ptc_agent/config/agent.py:348
module = __import__(module_name, fromlist=[class_name])
- recent drift+12 capability drift →
[](https://mcpobservatory.com/servers/github:Chen-zexi/open-ptc-agent/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 Chen-zexi.