Skills/npm/krs-poland-mcp-server

krs-poland-mcp-server@1.6.0

VERIFIED

Publisher claims: "The MCP server for KRS Poland public API." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher pkolawa · publishing for 435 daysInstalls 1,052Last detonated 13 min ago
$claude mcp add krs-poland-mcp-server -- npx -y krs-poland-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
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso ms.gov.pl — not the publisher's domain; check what for before connecting.
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 under the guard; read the third-party hosts first. The code names ms.gov.pl as well as its own vendor. The guard pins the network to the hosts the honeypot saw.

$vet-skills run --net declared -- npx -y krs-poland-mcp-server

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 1.3.5

vet-skills diff krs-poland-mcp-server 1.3.5 1.6.0

This version reaches for something 1.3.5 did not: 4 new tools (Check_KRS_Status, Check_KRS_Watchlist, Get_KRS_Entity_Profile, Get_KRS_Entry_History) · 2 rewritten tool descriptors (Get_Current_KRS_Record, Get_Full_KRS_Record). Compared from the two recorded runs, not from source.

New tools
Check_KRS_Status, Check_KRS_Watchlist, Get_KRS_Entity_Profile, Get_KRS_Entry_History
Rewritten tool descriptors
Get_Current_KRS_Record, Get_Full_KRS_Record

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-21 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 · 37 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
17sprocessdependency install exit 0
37sclaimed6 tools: Get_Current_KRS_Record, Get_Full_KRS_Record, Check_KRS_Status, Check_KRS_Watchlist, Get_KRS_Entry_History, Get_KRS_Entity_Profile
37stoolsc2e0ec23a7af6c07
37stools68a93263d52708a6
37stools22d210a5b24ba06d
37stools3d6b11d0de7269e0
37stools4cf376fc293383cc
37stools794b621e9bb2cdce
37sprocessscript backend runs setup only
37sprocessno install scripts to re-run

Static findings

No findings across 2,147 lines in 5 files.

Cost to the agent

Instructions loaded
≈51 tok
1 file · 5 in bundle
Tool list per prompt
≈2,213 tok
6 tools · 369 per tool
Handshake
570 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 545

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

Not checked against OSV yet; the weekly check has not reached this version.