ru-legal-skills-mcp@0.3.1
VERIFIED· not startedPublisher claims: "Unified MCP server для ru-legal-skills — все 33 tools + 186 skills РФ legal AI в одном пакете. Подключи в Claude Code / Cursor / любой MCP-клиент." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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
ANTHROPIC_API_KEYDEEPSEEK_API_KEYGIGACHAT_API_KEYOPENAI_API_KEYYC_IAM_TOKENConfiguration, not credentials: LLM_BASE_URL, LLM_MODEL, RU_LEGAL_ROUTER_LLM, YC_FOLDER_ID- Where it talks to
- no vendor host named in the codeAlso deepseek.com, yandex.net, sberbank.ru — 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 deepseek.com, yandex.net, sberbank.ru as well as its own vendor. The guard injects ANTHROPIC_API_KEY, DEEPSEEK_API_KEY, GIGACHAT_API_KEY, OPENAI_API_KEY, YC_IAM_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.
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 2026-11-16 and scored it 91/100 (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 deviationsStatic findings
patентнаяFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.АLFАFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.PatentоваяFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.purчaselyFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.ПреservationFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.гитXфлексFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.reлatesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.CвышеFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.матерyFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.demпингFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.distribuитсяFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.quartирыFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.syncатьсяFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.potребительскихFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.refundуFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.сlopeFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.resеrvesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.fабрикуетFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.СEOFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.командaFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.defenьватьFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.АлlegedFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.РеgistrarFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.SubjectivнаяFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.drafтFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.ЗаfiхFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.suдFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.реgistrarFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.npx license-checker --markdownFix: Pin versions and sources; vendor anything fetched at install time.compанияFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.регistryFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.npx license-reportFix: Pin versions and sources; vendor anything fetched at install time.Cost to the agent
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.