Skills/PyPI/nano-vm-mcp

nano-vm-mcp@0.5.0

VERIFIED· not started

Publisher claims: "MCP server for llm-nano-vm — run deterministic LLM programs via Model Context Protocol" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher ale007xd · publishing for 195 daysInstalls 284Last detonated 4 h ago
$claude mcp add nano-vm-mcp -- uvx nano-vm-mcp
WatchReport an issue

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
AGENT_DEBUGGER_TOKENConfiguration, not credentials: AGENT_DEBUGGER_URL, NANO_VM_MCP_DB, NANO_VM_MCP_HOST, NANO_VM_MCP_LLM_MODEL, NANO_VM_MCP_PORT
Where it talks to
no vendor host named in the codeAlso railway.app — 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
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 railway.app as well as its own vendor. The guard injects AGENT_DEBUGGER_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx nano-vm-mcp

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 2026-11-14 and scored it 83/100 (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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsnano_vm_mcp/cli.py:47 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdefault=".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsnano_vm_mcp/cli.py:48 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileshelp="Path to .env file (default: .env).",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_auth_policy.py:152 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""The decision runs after .env is loaded: a key in .env counts."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload action.github/workflows/log-to-ip-repo.yml:67 · File type combined with upload action — agent may exfiltrate local data filesSOURCE_LOG="${{ steps.log.outputs.log_file }}"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload action.github/workflows/log-to-ip-repo.yml:66 · File type combined with upload action — agent may exfiltrate local data filesBRANCH_DIR="${{ steps.log.outputs.branch_dir }}"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsnano_vm_mcp/cli.py:56 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Load .env before importing server (server reads env at module level)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandopencode.json:42 · Privileged sudo command — agent may execute with elevated privileges"sudo *": "deny",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_auth_policy.py:156 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_file = tmp_path / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈865 tok
3 files · 44 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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 nano-vm-mcp@0.5.0 as of 3 h ago. This is the package itself, not its dependencies.