Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/bulatko/vk-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/bulatko/vk-mcp-server/vk)<a href="https://agentmods.dev/mcp/bulatko/vk-mcp-server/vk"><img src="https://agentmods.dev/badge/mcp/bulatko/vk-mcp-server/vk/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/bulatko/vk-mcp-server/vk"><img src="https://agentmods.dev/badge/mcp/bulatko/vk-mcp-server/vk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
vk scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"vk": {
"command": "npx",
"args": [
"-y",
"vk-mcp-server"
],
"env": {
"VK_ACCESS_TOKEN": ""
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 12 lines scan A 4a23ab89691f
vk is an MCP server published in the GitHub repository bulatko/vk-mcp-server (16 stars, last pushed 11d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
youtube-summarize
MCP server that fetches YouTube video transcripts and optionally summarizes them. Runs locally from the youtube-summarize Python package.
stickyinc
A reification layer between LLM conversations and your commitments. MCP server + floating pane. Runs locally from the stickyinc npm package.
model-council
An MCP server that lets your assistant consult other LLMs — ask them, compare their answers, and synthesize a conclusion. Runs locally from the model-council-mcp Python package. Needs 9 environment variables to run.
savecontext
MCP server "savecontext" as configured in AlexanderBoger/SaveContext. Runs savecontext with python. Needs 1 environment variable to run.
prolog-reasoner
LLM-powered logical reasoning with Prolog - Calculator for logic. Runs locally from the prolog-reasoner Python package.
llm-wiki-mcp
MCP server + Claude Code skills for Karpathy-style LLM wikis: persistent markdown knowledge bases your agent grows over time. Runs locally from the llm-wiki-mcp Python package.