Atlas runs on your own machine — the client starts it, so there is no endpoint to ping. 54 installs a week from npm. Last commit 17 Sep 2026.
Atlas is a YAML-defined semantic layer for analytics — authored by humans, consumed by AI agents.
We read the source, 48 min ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
этот файл ставится пользователю, но в репозитории его нет
const proc = Bun.spawn(cmd, { stdout: "ignore", stderr: "pipe" });
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
`To restore manually: rm -rf ${SEMANTIC_DIR} && cp -r ${BACKUP_DIR} ${SEMANTIC_DIR}\n`,
<div class="usage-desc">Full detail above 128px. Drop diagonal rays and base nodes at 64px (center ray only). Outline + apex circle at 24–48px. Solid filled triangle below 24px (favicons).</div>
? path.join(SEMANTIC_DIR, sourceArg, "entities")
const url = `https://api.telegram.org/bot${this.botToken}/getChat?chat_id=${encodeURIComponent(chatId)}`;
for (const key of Object.keys(process.env)) {
for (const entry of fs.readdirSync(src, { withFileTypes: true })) {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add atlas -- npx -y @useatlas/mcp
{
"mcpServers": {
"atlas": {
"args": [
"-y",
"@useatlas/mcp"
],
"command": "npx"
}
}
}
[mcp_servers.atlas]
command = "npx"
args = ["-y", "@useatlas/mcp"]
{
"mcpServers": {
"atlas": {
"args": [
"-y",
"@useatlas/mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"atlas": {
"args": [
"-y",
"@useatlas/mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
ATLAS_DATASOURCE_URL (Analytics datasource URL (postgres, mysql, clickhouse, snowflake, duckdb, bigquery, salesforce). Optional — falls back to a bundled NovaMart SQLite demo when unset.), ATLAS_PROVIDER (LLM provider: anthropic, openai, bedrock, ollama, openai-compatible, gateway. Optional — the MCP server does not call an LLM directly (the client does); set this only if you also run Atlas's chat or scheduler.), ATLAS_API_URL (URL of a running Atlas API. Optional — defaults to http://localhost:3001. When set, the MCP server inherits the API's connections, semantic layer, and governance.).
The author declared them in the registry entry; get the values from the project itself.
The Marketing Data Layer for AI Agents - SEO, Search Console, and Analytics
Define, ship & query your analytics tracking from one source of truth, trusted by humans and agents.
Semantic, format-aware diff of config files (JSON/YAML/TOML/INI/.env/XML/CSV) for AI agents
Google Search Console for AI agents: search analytics, sitemaps, URL inspection.
Managed database, auth, file storage, email, analytics, and deployment for coding agents.
MCP server for picoli.site - URL shortening and click analytics for AI agents
Crypto intelligence for AI agents. Hyperliquid trader analytics, cohorts, and live market data.
Local-first AI CLI usage analytics for agents.
Answers built from our own checks of this server.