nephis-mcp-server@1.0.7
CAUTIONPublisher claims: "Model Context Protocol (MCP) Server for NEPHIS: Sub-6ms MicroVM Sandboxes, Zero-Copy Database Branching, and Execution Fabric for AI Coding Agents" Observed in sandbox: no network, 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
CIEL_API_KEYNEPHIS_API_KEYTHANATON_API_KEYConfiguration, not credentials: CIEL_BASE_URL, CIEL_EMAIL, CIEL_NAME, ESCHATON_API_URL, MNEMON_API_URL, NEPHIS_API_URL, NEPHIS_BASE_URL, NEPHIS_DEVELOPER_EMAIL, NEPHIS_DEVELOPER_NAME, NEPHIS_EMAIL, NEPHIS_NAME, THANATON_API_URL- Where it talks to
- theeducode.com (its own)
- What we saw when it ran
- no credential files read · no network
- What we could not test
- what the tools do when called with real credentials
Connect it with a scoped credential, under the guard. It asks for CIEL_API_KEY, NEPHIS_API_KEY, THANATON_API_KEY and talks to theeducode.com. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind.
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 2026-11-20 and scored it 77/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Host or command assembled from base64 fragments. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 26 s · 2 scenarios · 0 deviationsStatic findings
runnerCmd = `npx -y tsx -e "eval(Buffer.from('${b64}', 'base64').toString('utf-8'))"`;Fix: Pin versions and sources; vendor anything fetched at install time.output_filename: { type: "string", default: "output.txt", description: "Expected output file to read and grade" },Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.input_filename: { type: "string", default: "input.txt", description: "Input file name to seed" },Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.runnerCmd = `echo '${b64}' | base64 -d | bash`;Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.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 nephis-mcp-server@1.0.7 as of 38 min ago. This is the package itself, not its dependencies.
What would make this Verified
3 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim mohitrajdeo: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Obfuscated code≈ +5 on the totalRemove base64-assembled strings, eval of decoded text and minified blobs. Reviewers and scanners both treat unreadable code as hostile.
- Host or command assembled from base64 fragments≈ +4 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.