Skills/npm/ai-operator-mcp

ai-operator-mcp@1.0.0

VERIFIED· not started

Publisher claims: "MCP server for the Flyle AI Operator public API" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher flyle · publishing for 51 daysInstalls 16,209Last detonated 7d ago
$claude mcp add ai-operator-mcp -- npx -y @flyle/ai-operator-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

Code inventory arrives with this version's next honeypot run.
It will ask for
unknown until the next run
Where it talks to
unknown until the next run
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Not enough was observed to say yet. Not started: dependency install failed; the server itself was not observed. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try ai-operator-mcp` runs it now and prints the full answer.

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 2026-11-07 and scored it 82/100 (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 · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.7sprocessdependency install exit 1
0.8sprocessexec /usr/bin/date
0.8sprocessexec /usr/bin/timeout
0.8sclaimedno tools/list reply (exit 0)
0.8sprocessscript backend runs setup only
0.8sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionmain.js:29 · File type combined with upload action — agent may exfiltrate local data filesfunction R(e,t,n){let r=e[`~run`]({value:t},/* @__PURE__ */ me(n));return{typed:r.typed,success:!r.issues,output:r.value,issues:r.issues}}const Ie=e=>{let t=e.length;for(;t>0&&e[t-1]===`/`;)--t;returnFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandmain.js:2 · File permission modification command — agent changes file ownership/permissionsimport{homedir as e,hostname as t,userInfo as n}from"node:os";import{serveStdio as r}from"@modelcontextprotocol/server/stdio";import{createHash as i,randomBytes as a,timingSafeEqual as o}from"node:cryFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packagemain.js:29 · npx invocation of non-well-known package — may execute untrusted codefunction R(e,t,n){let r=e[`~run`]({value:t},/* @__PURE__ */ me(n));return{typed:r.typed,success:!r.issues,output:r.value,issues:r.issues}}const Ie=e=>{let t=e.length;for(;t>0&&e[t-1]===`/`;)--t;returnFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionmain.js:32 · File type combined with upload action — agent may exfiltrate local data files`,i)?2:1;e=e.slice(i+a);let s=o(n);s!=null&&r.push(s),i=e.search(wt)}return r},hasPendingIncomplete:()=>e!==``||r.length>0,flush:()=>(e=``,t=!1,n=``,r=[],[])}},Et=async(e,t)=>{if(t<=0)return`deadline`Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
URL with embedded credentialspackage.json:1 · URL with embedded credentials — may be phishing or credential leaking{"name":"@flyle/ai-operator-mcp","version":"1.0.0","description":"MCP server for the Flyle AI Operator public API","keywords":["flyle","mcp","modelcontextprotocol"],"license":"SEE LICENSE IN LICENSE",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
npx invocation of non-well-known packagemain.js:32 · npx invocation of non-well-known package — may execute untrusted code`,i)?2:1;e=e.slice(i+a);let s=o(n);s!=null&&r.push(s),i=e.search(wt)}return r},hasPendingIncomplete:()=>e!==``||r.length>0,flush:()=>(e=``,t=!1,n=``,r=[],[])}},Et=async(e,t)=>{if(t<=0)return`deadline`Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)main.js:2 · MCP server using network transport (SSE/HTTP) — data sent over networkimport{homedir as e,hostname as t,userInfo as n}from"node:os";import{serveStdio as r}from"@modelcontextprotocol/server/stdio";import{createHash as i,randomBytes as a,timingSafeEqual as o}from"node:cryFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
File type combined with upload actionmain.js:94 · File type combined with upload action — agent may exfiltrate local data files- ファイルの取り込みは inspect_local_file → create_knowledge_upload_urls → upload_file → create_knowledge_import の順に進め、取り込みとドキュメントの処理完了を確認します。API の byteSize には sizeBytes、checksumSha256 には sha256Hex を渡します(sha256Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈51 tok
1 file · 5 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 @flyle/ai-operator-mcp@1.0.0 as of 7d ago. This is the package itself, not its dependencies.