§ MCP/Behavioral grade
B
https://mcp.acp.virtuals.io
litmus-v14 · 2026-07-06
- C-01 Tool-output injection
- pass
- C-02 Permission / egress overreach
- skipped — egress not run for this target
- C-03 Sensitive-data handling
- pass
- C-04 Adversarial-input handling
- pass
tool-defs fingerprint · 0xa19e51…01718
Why B: Injection checks passed; egress not verified. Not verified: C-02 (egress not run for this target).
How to fix this →
Guided remediation — the specific changes that clear this grade.
Reproduce this grade
The harness is open and deterministic. Re-run it against the same server and compare the grade and fingerprint — a false grade is falsifiable, not merely disputable.
npx -p @polygraphso/litmus polygraphso-litmus https://mcp.acp.virtuals.ioEmbed this badge
Drop it in a README, docs site, or package page. It always shows the current published grade and links back here.
Markdown — badge
[](https://polygraph.so/mcp/https/mcp.acp.virtuals.io)HTML — badge
<a href="https://polygraph.so/mcp/https/mcp.acp.virtuals.io"><img src="https://polygraph.so/api/badge?server=https/mcp.acp.virtuals.io" alt="polygraph grade"></a>Markdown — card
[](https://polygraph.so/mcp/https/mcp.acp.virtuals.io)Questions
- What does polygraph's B grade mean for https://mcp.acp.virtuals.io?
- It’s a behavioral grade on an A–F scale. polygraph connected to https://mcp.acp.virtuals.io the way an agent would, exercised its tools, and watched what it did — whether it tried to hijack the caller, send data off-box, leak planted secrets, or mishandle adversarial input. B is where that evidence placed it. It describes behavior on the day it ran, not a guarantee.
- What did polygraph test?
- Four probe categories, run against the live server in a sandbox: C-01 tool-output injection, C-02 permission and egress overreach, C-03 sensitive-data handling, and C-04 adversarial-input handling. The full battery is in the methodology.
- How do I reproduce this grade?
- Run
npx -p @polygraphso/litmus polygraphso-litmus https://mcp.acp.virtuals.io. The harness is open and deterministic, so anyone can re-run it against the same server and disprove a false grade — reproducibility is what the grade rests on. - Can a server pay polygraph for a better grade?
- No. Independence is disclosure-based: material support must be publicly registered, and no graded party gets review or approval rights over its letter. The grade is set by the evidence, not the relationship.