LemmaBase MCP

LemmaBase MCP lets you connect an AI assistant to LemmaBase so it can work with your published rules. It can search the registry, read a spec, run it with sample data, and help you write or review Lemma source.

The connection is read-only. Your assistant cannot publish or change anything on LemmaBase. Publish from the editor first, then point your client at the published version.

Connecting

Add this URL in your MCP client settings:

https://lemmabase.com/mcp

Public repositories work without credentials. To include private repositories or organization repositories you belong to, add a LemmaBase API token. Create a personal token under Dashboard → Settings. Organization service tokens are managed in that organization’s settings. See Using your specs for the token format.

What your assistant can do

Once connected, your assistant can search for public rules on LemmaBase, list what is in a repository, inspect what inputs a spec expects, and run a spec to see the results. It can also check Lemma source you paste in, or draft new source from a description you give it.

If a rule changed on a particular date, you can ask for results as of that date. The syntax for temporal rules is on Lemma.run (opens in new tab) .

VS Code / Antigravity / Cursor

In your editor’s MCP settings, add a server entry like this:

{
  "mcpServers": {
    "lemmabase": {
      "url": "https://lemmabase.com/mcp",
      "headers": {
        "Authorization": "Bearer lmb_YOUR_TOKEN"
      }
    }
  }
}

Omit the headers block if you only need public repositories.

Claude Desktop

Add the same URL and optional token to claude_desktop_config.json under mcpServers.

Gemini CLI

Configure mcpServers in your Gemini CLI settings with the LemmaBase URL and optional Bearer token.

Public and private specs

The LemmaBase MCP server has access to all Lemma specs on the platform that your account can see. Public specs are available to everyone. With a token, your assistant can also reach your private repositories and organization repositories you belong to.

Use it when you want your assistant to reference what others have published: look up a spec someone shared, read how it is structured, run it with sample input, or compare it with rules you are writing. Everything comes from published versions on LemmaBase, not from drafts on your machine.

That makes it useful when you build on existing work. Your assistant can find a VAT or pricing spec in the registry, inspect its inputs and rules, and help you wire it into your own repository or explain what a published result means.

LLMs explains the llms.txt fallback for clients that do not support MCP.

Registry search lets you browse public rules in the browser.