Skills/PyPI/perplexity-polza-mcp-server

perplexity-polza-mcp-server@0.1.1

VERIFIED

Publisher claims: "An MCP server for Perplexity models through the Polza.ai chat API" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher ivanantigravity-lgtm · publishing for 208 daysInstalls 269Last detonated 1 h ago
$claude mcp add perplexity-polza-mcp-server -- uvx perplexity-polza-mcp-server
WatchReport an issue

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
API_KEYPOLZA_AI_API_KEYPOLZA_API_KEYConfiguration, not credentials: COUNCIL_CHINA_DEEPSEEK_MODEL, COUNCIL_CHINA_MOONSHOT_MODEL, COUNCIL_CHINA_QWEN_MODEL, COUNCIL_USA_GEMINI_MODEL, COUNCIL_USA_GROK_MODEL, COUNCIL_USA_OPENAI_MODEL, PERPLEXITY_MODEL, PERPLEXITY_RESEARCH_MODEL, POLZA_BASE_URL, SEEDANCE_MAX_WAIT, SEEDANCE_MODEL, SEEDANCE_POLL_INTERVAL
Where it talks to
no vendor host named in the codeAlso polza.ai — 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 real credentials

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names polza.ai as well as its own vendor. The guard injects API_KEY, POLZA_AI_API_KEY, POLZA_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx perplexity-polza-mcp-server

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 2026-11-14 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 · 25 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
4.7sprocessdependency install exit 0
25sclaimed3 tools: perplexity_ask, perplexity_research, list_perplexity_models
25stools09babfdfe7995082
25stools9f083e2e0d62d085
25stoolsc7bbb2bf4f9f7ecb
25sprocessscript backend runs setup only
25sprocessno install scripts to re-run

Static findings

No findings across 4,409 lines in 44 files.

Cost to the agent

Instructions loaded
≈1,013 tok
3 files · 44 in bundle
Tool list per prompt
≈501 tok
3 tools · 167 per tool
Handshake
446 ms
launch to tools/list, stdio
Undocumented tools
3
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 perplexity-polza-mcp-server@0.1.1 as of 47 min ago. This is the package itself, not its dependencies.