Tagging

MCP powered by Polar Llama

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 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": {
    "daviddrummond95-tagging_mcp": {
      "command": "uv",
      "args": [
        "run",
        "fastmcp",
        "run",
        "/path/to/tagging_mcp/tagging.py"
      ],
      "env": {
        "GROQ_API_KEY": "YOUR_KEY_HERE",
        "GEMINI_API_KEY": "YOUR_KEY_HERE",
        "OPENAI_API_KEY": "YOUR_KEY_HERE",
        "ANTHROPIC_API_KEY": "YOUR_KEY_HERE"
      }
    }
  }
}

You can rapidly tag CSV rows in parallel using multiple LLM providers with MCP. This server leverages polar_llama to process rows concurrently, enabling fast batch tagging, flexible taxonomies, and optional reasoning for transparency.

How to use

You interact with the tagging MCP by running a local MCP client that talks to your configured MCP servers. Start the servers, then use their tagging tools to process CSV files. The system supports creating a simple single-field tag as well as advanced multi-field classifications. You can include reasoning and confidence scores in the output for full visibility.

How to install

Prerequisites you need before installation are Python 3.12 or newer and the UV package manager. You also need API keys for at least one compatible LLM provider (Anthropic Claude, OpenAI, Gemini, or Groq). Make sure you have a working environment where you can run commands from your shell.

Configuration and usage notes

This server provides two local development configurations via a Claude Desktop setup. Both configurations run as stdio MCP servers and should be launched from your MCP client. Each one runs in parallel against your CSV data and uses your chosen LLM providers through environment variables.

Troubleshooting and tips

If you encounter missing API keys or invalid provider selections, verify that the environment variables ANTHROPIC_API_KEY, OPENAI_API_KEY, GEMINI_API_KEY, and GROQ_API_KEY are available to the MCP processes. Check that your CSV input is well-formed and that the selected taxonomy aligns with the column you target for analysis. If a tag field is not appearing in the output, confirm that the tagging function is invoked and that the CSV row contains the expected text column.

Additional considerations

You can enable optional reasoning for tags to get detailed explanations, confidence levels, and reflections. This helps you audit the tagging decisions and adjust taxonomies as needed.

Available tools

tag_csv

Simple tagging with a list of categories and optional reasoning. Produces a dictionary with status, a preview, confidence scores, and optional errors.

tag_csv_advanced

Advanced multi-field tagging using a full taxonomy dictionary. Returns a complete set of values with confidence per field and optional reasoning.

preview_csv

Preview the first few rows of a CSV to understand structure, returning columns, row count, and sample data.

get_tagging_info

Retrieve server metadata, supported providers, features, and available tools.