MCP servers · atlasdevhq

Atlas: YAML semantic layer for AI agent analytics

An MCP server that exposes a YAML-defined semantic layer for analytics, so AI agents can answer questions from company data and approved facts.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

Atlas is a semantic layer for analytics, defined in YAML by people and consumed by AI agents through MCP. Each answer states which of three kinds of material it draws on: data read live from the company's own sources through the semantic layer, where queries are SELECT-only, single-statement, limited to whitelisted tables and validated before they run; facts extracted from written material and approved by a named person, which keep their source and date; or unedited raw source material. Live data takes precedence over approved facts where they overlap, and contradictions are shown with both sources instead of being resolved.

The server suits teams that want an AI client such as Claude Desktop, Cursor or Continue to answer questions about company data with visible provenance. A local instance with no datasource configured uses bundled NovaMart demo data, so the setup can be tried before connecting real sources.

Running it means self-hosting the complete Atlas server, which is licensed under AGPL, inside your own environment, with Docker, Railway or Vercel as listed deployment options. Clients are connected through the package's init command, either against a local instance or against a self-hosted one with managed authentication. Documentation has moved into the project's docs source.

Limitations and requirements

The hosted service at useatlas.dev has been shut down, so only self-hosted or local operation is available. The server and core packages are AGPL-3.0, and modifications served to users must be shared. The ee/ directory is under a commercial license and covers governance, convenience and scale features. Connecting to a self-hosted instance with managed auth requires that instance to be set up.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    Atlas

    Atlas is a YAML-defined semantic layer for analytics — authored by humans, consumed by AI agents.

    v0.0.2
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
docker

Docker Hub MCP Server

Docker's MCP server that helps an AI assistant find and compare container images on Docker Hub and, with your token, manage your own repositories and tags.

171 GitHub starsCloud & DevOpsSoftware development
Updated 13 Nov 2026
MCP servers
awslabs

MCP servers for AWS (AWS Labs)

A large open-source collection of MCP servers from AWS Labs for building and operating on AWS: documentation, infrastructure, databases, AI services, cost and more.

9.9K GitHub starsCloud & DevOpsData & databases
Updated 17 Nov 2026
MCP servers
firecrawl

Firecrawl MCP Server (web search and scraping)

Firecrawl's MCP server that lets an AI assistant search the web, turn pages and PDFs into clean Markdown, crawl sites and interact with dynamic pages.

7.8K GitHub starsWeb, search & browserProductivity & automation
Updated 17 Nov 2026
MCP servers
microsoft

Playwright MCP (browser automation)

Microsoft's MCP server that lets an AI assistant open web pages, click, type and read them through a real browser, using the page structure instead of screenshots.

39.6K GitHub starsTesting & QAWeb, search & browser
Updated 18 Nov 2026
Atlas: YAML semantic layer for AI agent analytics | AI Gate Discover