Skip to content
MCP server

Atlantic Agentic Labs

Search and read Atlantic Agentic Labs' public LightHouse docs with exact quotations

Status and history

Answered our latest tool-list check 9 hours ago with 4 tools. It will be marked verified after 3 successful checks in 7 days.

Pricing
Free
Platforms
API, Web
Runs
Remotely
Version
1.0.0
Listing updated
3 days ago

About Atlantic Agentic Labs

Atlantic Agentic Labs is a free MCP server for knowledge and memory. It runs as a hosted remote server, so there is nothing to install locally.

Atlantic's server returns passages quoted word for word, never generated answers. Each result carries a deep link to the page and section, the source version or date and evidence fields, so the assistant can cite it. Search returns between 1 and 8 best-matching passages.

It covers the public LightHouse documentation, its API's OpenAPI document and MCP reference, plus the items on Atlantic's knowledge pages. LightHouse is Atlantic's product for managing an organisation's AI agents, models, approvals, access and billing in the customer's own cloud or servers. This public server is separate from LightHouse's own MCP server, which reads a tenant and requires sign-in. It reads no tenant data and offers no prices or commitments.

No account is needed. Requests over the rate limit get HTTP 429 with a Retry-After header, and queries are kept for 12 months with emails, numbers and tokens redacted.

Install

Run in a terminal

claude mcp add --transport http ask https://ask.atlanticagenticlabs.com/mcp

Add to Settings → Connectors → Add custom connector

https://ask.atlanticagenticlabs.com/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "ask": {
      "url": "https://ask.atlanticagenticlabs.com/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "ask": {
      "type": "http",
      "url": "https://ask.atlanticagenticlabs.com/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "ask": {
      "serverUrl": "https://ask.atlanticagenticlabs.com/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "ask": {
      "type": "http",
      "url": "https://ask.atlanticagenticlabs.com/mcp"
    }
  }
}

Tools this server provides (4)

Read directly from the server.

search_docs
Search Atlantic's public LightHouse™ documentation, including the API reference (OpenAPI) and the MCP tool reference. Use it for any question about what LightHouse does and how: connectors, agents, approvals, spend limits, evidence, security, deployment, the API, the MCP server and the CLI. Returns up to `limit` passages, best first, each quoted exactly with a deep link (`url`), the docs version a
search_published_knowledge
Search the items Atlantic Agentic Labs has published about how it works: how engagements run, its technology partners, its positioning and its use cases. Use it for questions about Atlantic as a company rather than the product's mechanics. Returns passages quoted exactly, each with a link to the published item, its revision and publication date; `covered` is false when nothing published answers th
list_pages
The public documentation's table of contents: for each page its section, title, path, URL and a one-line description, in the order the site shows them, with the list of sections, showing what the documentation covers. Optional `section` (one of the returned `sections`, matched without regard to case) narrows the list.
read_page
One public documentation page as Markdown, exactly as published, with its title, canonical URL, section and the date it last changed. It takes a path or URL on the documentation site, such as "/mcp/public/" or "https://docs.atlanticagenticlabs.com/mcp/public/". Only pages of the public documentation site are served: any other address, and any page not in the published index, is refused. A very lon

What it does

Exact quotations
Passages are returned verbatim with deep links.
Evidence fields
Results include the source version or date.
Whole-page reads
read_page returns a docs page as Markdown, truncated with a note if very long.
Contents listing
list_pages gives sections, titles, paths and short descriptions.
No credentials
Connect without sign-in, OAuth or headers.

Good for

  • Cite LightHouse documentation in an answer
  • Look up an API field from the OpenAPI document
  • Browse Atlantic's published knowledge items
  • Read a docs page in an agent's context

Pricing

Free

Free, no account

Prices change. Check docs.atlanticagenticlabs.com before you buy.

Atlantic Agentic Labs FAQ

Do I need an account?

No. The server is unauthenticated and has no access to any tenant.

Does it generate answers?

No. The connected assistant writes its reply from the quoted passages.

How long are queries kept?

12 months, with emails, phone numbers, keys and tokens redacted.

What happens at the rate limit?

The server returns HTTP 429 with a Retry-After header.

Is Atlantic Agentic Labs free?

Yes. Atlantic Agentic Labs is free to use.

How do I add Atlantic Agentic Labs to Claude Code?

Run this command in your terminal: claude mcp add --transport http ask https://ask.atlanticagenticlabs.com/mcp

What are the best alternatives to Atlantic Agentic Labs?

The closest alternatives to Atlantic Agentic Labs are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Atlantic Agentic Labs

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools