mcp@2.5.1
VERIFIEDPublisher claims: "A Model Context Protocol Server for One" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Started with a decoy ONE_SECRET; tool list observed. Tool calls with a real credential not tested.- Tested
- server startup with a tagged decoy in ONE_SECRET · MCP initialize and tools/list · every tool description, for hidden instructions · where the decoy credential went · every file read, file written and host contacted by what ran
- Not tested
- what the tools do when called with a real credential
- Needs
- ONE_SECRET — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.
Before you give it your token
- It will ask for
ONE_SECRETConfiguration, not credentials: ONE_ACTION_IDS, ONE_APPROVAL, ONE_BASE_URL, ONE_CONNECTION_KEYS, ONE_IDENTITY, ONE_IDENTITY_TYPE, ONE_KNOWLEDGE_AGENT, ONE_PERMISSIONS- Where it talks to
- withone.ai (its own)Also nodejs.org, some-vendor-api.com — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- what the tools do when called with a real credential
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names nodejs.org, some-vendor-api.com as well as its own vendor. The guard injects ONE_SECRET only into requests to withone.ai (and its subdomains) and refuses the rest.
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 2026-11-11 and scored it 95/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 46 s · 2 scenarios · 0 deviationsStatic findings
No findings across 4,084 lines in 25 files.
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 @withone/mcp@2.5.1 as of 3d ago. This is the package itself, not its dependencies.