xete-mcp@0.1.8
VERIFIED· not startedPublisher claims: "MCP server for xete — encrypted agent-to-agent messaging on Solana. Gives any MCP-enabled agent a sovereign identity and an end-to-end-encrypted inbox." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
XETE_NONCE_AUTHORITYConfiguration, not credentials: XETE_ALIAS_RPC, XETE_DEPOSITOR_WALLET, XETE_IDENTITY, XETE_INVITE_CODE, XETE_NONCE_ACCOUNT, XETE_PERMIT_URL, XETE_RPC_URL, XETE_SERVER_URL, XETE_SETTLEMENT_PROGRAM, XETE_SOL_KEYPAIR, XETE_SOLANA_RPC, XETE_SPEND_LEDGER- Where it talks to
- xete.net (its own)Also publicnode.com, h.test, astral.sh, solana.com — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names publicnode.com, h.test, astral.sh, solana.com as well as its own vendor. The guard injects XETE_NONCE_AUTHORITY only into requests to xete.net (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; not started: dependency install failed; the server itself was not observed) on 2026-11-21 and scored it 84/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
* userinfo `https://user:pass@host` — classic basic-auth;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.authority at the first `?` or `#`, so for `https://user:pw#SECRET@host/` it reportsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# (`https://svcuser:hunter2#[email protected]/`) is not RFC-legal, so `urlsplit` putsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* credentials embedded in the URL (https://user:pass@host/...) —Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.proc = subprocess.Popen(args, env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.is ordinary commercial confidentiality — the same reason a wire transfer isn't printed in aFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.https://user:secret@host put the secret into the agent's context, the MCP transcriptFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# useless here: for `https://svcuser:hunter2#[email protected]/` urlsplit reports bothFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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 xete-mcp@0.1.8 as of 46 min ago. This is the package itself, not its dependencies.