Skills/npm/privco-data-mcp

privco-data-mcp@1.7.1

VERIFIED

Publisher claims: "This package provides MCP (Model Context Protocol) handlers for accessing PrivCo's data services." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher github actions · publishing for 414 daysInstalls 903Last detonated 4d ago
$claude mcp add privco-data-mcp -- npx -y privco-data-mcp
WatchReport an issue

Coverage

Started with a decoy PRIVCO_API_KEY; tool list observed. Tool calls with a real credential not tested.
Tested
server startup with a tagged decoy in PRIVCO_API_KEY · MCP initialize and tools/list · every tool description, for hidden instructions · where the decoy credential went · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with a real credential
Needs
PRIVCO_API_KEY — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.

Before you give it your token

It will ask for
PRIVCO_API_KEYConfiguration, not credentials: PRIVCO_API_BASE_URL
Where it talks to
no vendor host named in the codeAlso privco.com — 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 a real credential

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

$vet-skills run --net declared -- npx -y privco-data-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) on 2026-11-10 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 · 46 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
6.0sprocessdependency install exit 0
26sprocessrelaunched with a decoy PRIVCO_API_KEY (tagged; nothing real)
46sclaimed18 tools with a decoy PRIVCO_API_KEY: match, profile, general_profile, people, financials, revenue_financials, identification, ma_deals, vc_deals, people_search, company_search, company_similar, funding_search, deal_search, industry_keyword, industry_pics, company_contact, investor_contact
46sprocessscript backend runs setup only
46sprocessno install scripts to re-run

Static findings

LOW
Coercive compliance languagedocs/usage-guide.md:282 · Coercive compliance language · informational: not an instruction file…mary`, funding-round detail, M&A detail If you need any of the omitted fields, you must follow up with `profile` per company. For round-level data, also `vc_deals`. For M&A d…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

No other findings across 3,036 lines in 64 files.

Cost to the agent

Instructions loaded
≈62 tok
1 file · 64 in bundle
Tool list per prompt
≈12,876 tok
18 tools · 715 per tool
Handshake
1148 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 1154

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 privco-data-mcp@1.7.1 as of 4d ago. This is the package itself, not its dependencies.