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/smigolsmigol/llmkitWrote 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/smigolsmigol/llmkit/mcp-server-llmkit)<a href="https://agentmods.dev/mcp/smigolsmigol/llmkit/mcp-server-llmkit"><img src="https://agentmods.dev/badge/mcp/smigolsmigol/llmkit/mcp-server-llmkit.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
llmkit 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 8d 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
{
"llmkit": {
"command": "npx",
"args": [
"-y",
"@f3d1/llmkit-mcp-server"
],
"env": {
"LLMKIT_API_KEY": "",
"LLMKIT_PROXY_URL": ""
}
}
}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.
- 8d ago First seen · 13 lines scan A c13593522907
llmkit is an MCP server published in the GitHub repository smigolsmigol/llmkit (16 stars, last pushed today), 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 2026-08-30.
Other mcp servers, from other repositories
promptspend
LLM pricing where every rate carries its source and the date it was last confirmed. Runs locally from the @promptspend/mcp npm package.
llm-cost-guard
Track LLM costs, set budget limits, get alerts. One command to install, one line to use. Runs locally from the @wimoron/llm-cost-guard npm package.
agentic-ledger
Runtime observability for AI agents — see exactly what your agent did, why it did it, and what it cost. Runs locally from the agentic-ledger Python package.
tools
476 MCP tools across 557 fintech tools: ChainGraph AP2 decisions, executionhash. Zero PII. Remote server at mcp.ainumbers.co.
shippage
Publish HTML or Markdown to a public URL in one call. Zero config, auto-registers on first use. Runs locally from the shippage-mcp npm package.
kainext-binance-mcp
MCP server for Binance spot: read market data, analyze, and propose real-money trades behind a human-gated confirmer. The model never holds a trade key. Runs locally from the kainext-binance-mcp Python package. Needs 3 environment variables to run.