APLCart

Exposes APLCart idioms with exact syntax lookup, keyword search, and OpenAI-powered semantic search.

python

0

GitHub Stars

python

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "xpqz-ac-mcp": {
      "command": "uv",
      "args": [
        "run",
        "python",
        "aplcart_mcp_semantic.py"
      ],
      "env": {
        "APLCART_USE_DB": "0",
        "OPENAI_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You run an MCP server that exposes the APLCart idiom collection with semantic search and fast syntax-based lookups. This server lets you find APL expressions by exact syntax, search across syntax and descriptions, retrieve keywords for expressions, and perform natural language queries using OpenAI embeddings.

How to use

Start the MCP server and connect with your MCP client to access APLCart capabilities. The server exposes four core tools: lookup-syntax for exact syntax matches, search for substring queries across syntax, description, and keywords, keywords-for to fetch keywords for a specific syntax, and semantic-search to perform natural language queries using embeddings. To get started, run the server in your environment and then issue requests through your MCP client to explore APLCart’s idioms and descriptions.

How to install

Prerequisites you need to satisfy before installation: Python 3.11 or higher, and an OpenAI API key for semantic search.

Install the MCP runtime utility (uv) if you have not already done so.

Set up your working directory and clone the project repository, then install dependencies with uv.

Install uv if you haven’t already, clone the repository, and install dependencies using uv sync.

Available tools

lookup-syntax

Find an exact APL idiom by matching the provided syntax exactly.

search

Search across syntax, descriptions, and keywords using substring matching.

keywords-for

Retrieve keywords associated with a specific APL syntax expression.

semantic-search

Perform natural language queries using embeddings for semantic results.

search_embeddings

Standalone tool to query embeddings and retrieve results in interactive or JSON mode.