full-vk-mcp@0.3.2
VERIFIEDPublisher claims: "Model Context Protocol server for VKontakte VK API" Observed in sandbox: calls github.com, codeload.github.com only, touches nothing outside the project, writes no memory.
Coverage
Started with a decoy VK_ACCESS_TOKEN; tool list observed. Tool calls with a real credential not tested.- Tested
- server startup with a tagged decoy in VK_ACCESS_TOKEN · 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
- VK_ACCESS_TOKEN — 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
VK_ACCESS_TOKENVK_MCP_AUTH_TOKENConfiguration, not credentials: VK_MCP_CORS_ORIGIN, VK_MCP_EXCLUDE_METHODS, VK_MCP_EXCLUDE_SECTIONS, VK_MCP_HOST, VK_MCP_INCLUDE_METHODS, VK_MCP_INCLUDE_SECTIONS, VK_MCP_MAX_TOOLS, VK_MCP_MODE, VK_MCP_PORT, VK_MCP_PROFILE, VK_MCP_TRANSPORT- Where it talks to
- no vendor host named in the codeAlso vk.com — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · reached only github.com, codeload.github.com
- 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 vk.com as well as its own vendor. The guard injects VK_ACCESS_TOKEN, VK_MCP_AUTH_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) 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: calls github.com, codeload.github.com only, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 52 s · 2 scenarios · 0 deviationsStatic findings
No findings across 1,789 lines in 13 files.
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
No advisories in OSV for full-vk-mcp@0.3.2 as of 6 h ago. This is the package itself, not its dependencies.