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/enessari/metabase-ai-assistantWrote 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/enessari/metabase-ai-assistant/metabase-ai-assistant)<a href="https://agentmods.dev/mcp/enessari/metabase-ai-assistant/metabase-ai-assistant"><img src="https://agentmods.dev/badge/mcp/enessari/metabase-ai-assistant/metabase-ai-assistant/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/enessari/metabase-ai-assistant/metabase-ai-assistant"><img src="https://agentmods.dev/badge/mcp/enessari/metabase-ai-assistant/metabase-ai-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
metabase-ai-assistant 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 12d 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
{
"metabase-ai-assistant": {
"command": "npx",
"args": [
"-y",
"metabase-ai-assistant"
],
"env": {
"METABASE_URL": "${METABASE_URL}",
"METABASE_USERNAME": "${METABASE_USERNAME}",
"METABASE_PASSWORD": "${METABASE_PASSWORD}",
"METABASE_API_KEY": "${METABASE_API_KEY}",
"DATABASE_HOST": "${DATABASE_HOST}",
"DATABASE_PORT": "${DATABASE_PORT}",
"DATABASE_NAME": "${DATABASE_NAME}",
"DATABASE_USER": "${DATABASE_USER}",
"DATABASE_PASSWORD": "${DATABASE_PASSWORD}"
}
}
}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.
- 12d ago First seen · 20 lines scan A a77b4e38aa70
metabase-ai-assistant is an MCP server published in the GitHub repository enessari/metabase-ai-assistant (49 stars, last pushed 9d ago), licensed Apache-2.0. 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
malloy
MCP server "malloy", hosted remotely at localhost, as configured in malloydata/publisher.
pbiviz
Command line tool for creating and publishing visuals for Power BI. Runs locally from the powerbi-visuals-tools npm package.
scala-score
MCP server for S.C.A.L.A. Score API — let Claude, ChatGPT, and AI agents search 250M+ companies. Runs locally from the scala-mcp-server npm package. Needs 1 environment variable to run.
corpusiq
MCP server "corpusiq", hosted remotely at mcp2.corpusiq.io, as configured in CorpusIQ/corpusiq-docs.
kokai
MCP server "kokai", hosted remotely at mcp.kokai.ai, as configured in Kokai-Data/japan-business-data.
business-intelligence
AI business intelligence: competitor analysis, web scoring, reviews, market research. Remote server at mcp.ezbizservices.com.