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/Lykhoyda/ask-llmWrote 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/lykhoyda/ask-llm/antigravity-mcp-ask-llm)<a href="https://agentmods.dev/mcp/lykhoyda/ask-llm/antigravity-mcp-ask-llm"><img src="https://agentmods.dev/badge/mcp/lykhoyda/ask-llm/antigravity-mcp-ask-llm/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/lykhoyda/ask-llm/antigravity-mcp-ask-llm"><img src="https://agentmods.dev/badge/mcp/lykhoyda/ask-llm/antigravity-mcp-ask-llm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ask-llm 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
{
"ask-llm": {
"command": "npx",
"args": [
"-y",
"@ask-llm/mcp"
],
"env": {
"XAI_API_KEY": "",
"ASK_GROK_HARNESS": "xai-api",
"ASK_GROK_MODEL": "",
"ASK_GROK_REASONING_EFFORT": "high",
"ASK_GROK_MAX_OUTPUT_TOKENS": "16384",
"ASK_GROK_TIMEOUT_MS": "600000",
"CURSOR_API_KEY": "",
"ASK_CURSOR_TIMEOUT_MS": "600000",
"ASK_CLAUDE_MODEL": "opus",
"ASK_CLAUDE_FALLBACK_MODEL": "sonnet",
"ASK_CLAUDE_TIMEOUT_MS": "600000",
"OLLAMA_HOST": "http://localhost:11434",
"ASK_ANTIGRAVITY_TIMEOUT_MS": "300000",
"ASK_ANTIGRAVITY_SANDBOX": "1",
"GMCPT_TIMEOUT_MS": "300000",
"GMCPT_LOG_LEVEL": "warn"
}
}
}What else server.json configures
This page is one entry in a file that holds 7. Installing the file brings all of them; each is measured and scanned on its own page.
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 Changed · +8 lines d8b1a50464a2
- 2mo ago First seen · 19 lines scan A f7c7ee8f6b98
ask-llm is an MCP server published in the GitHub repository Lykhoyda/ask-llm (19 stars, last pushed 6d 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 2026-08-30.
Other mcp servers, from other repositories
freellmpool
Free LLM gateway: 22 LLM providers, 178 enabled chat routes, 431 cataloged chat models; keyless start when available. Runs locally from the freellmpool Python package.
lm
Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model. Runs locally from the @houtini/lm npm package. Needs 4 environment variables to run.
promptheus
AI-powered prompt engineering CLI tool. Runs locally from the promptheus Python package. Needs 8 environment variables to run.
vox-mcp
Multi-model AI gateway for MCP clients — routes prompts to Gemini, OpenAI, Anthropic, xAI, DeepSeek, Moonshot, OpenRouter, Cloudflare AI Gateway, Vercel AI Gateway, and local models with conversation memory. Runs locally from the vox-mcp Python package. Needs 19 environment variables to run.
gemini-code-context-mcp
Gemini 2M context cache for Claude Code — persistent; repeat queries 8x faster, 4x cheaper. Runs locally from the @qmediat.io/gemini-code-context-mcp npm package. Needs 8 environment variables to run.
latent-gate
Local-first vision-language pipeline inspired by VL-JEPA. Compress images, text, conversations, and RAG documents locally via Ollama before sending to any LLM API. Deterministic, fact-preserving token optimizer plus MCP server, FastAPI server and video processing. Runs locally from the latent-gate Python package.