verify-mcp@0.1.0
VERIFIEDPublisher claims: "Free, no-account verification of KeyHalve-sealed documents. Read-only; never receives keys." Observed in sandbox: calls mcp.keyhalve.com only, touches nothing outside the project, writes no memory.
Coverage
Server started and answered tools/list.- Tested
- MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
- Not tested
- what the tools do when called with real credentials
Before you give it your token
- It will ask for
- no credential variables read in the code
- Where it talks to
- keyhalve.com (its own)
- What the honeypot saw
- no credential files read · reached only mcp.keyhalve.com (its own)
- What we could not test
- what the tools do when called with real credentials
Reasonable to connect. No credential asked for, no third-party host named, Server started and answered tools/list.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-10 and scored it 92/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: calls mcp.keyhalve.com only, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 22 s · 2 scenarios · 0 deviationsStatic findings
* clients (`npx @keyhalve/verify-mcp`) get byte-identical behavior to theFix: Pin versions and sources; vendor anything fetched at install time.Settings → Connectors → Advanced → Developer mode → Add server →Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.### ChatGPT (Developer mode — Plus/Pro/Business/Enterprise/Edu)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Settings → Connectors → Advanced → Developer mode → Add server →Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.### ChatGPT (Developer mode — Plus/Pro/Business/Enterprise/Edu)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for @keyhalve/verify-mcp@0.1.0 as of 4d ago. This is the package itself, not its dependencies.