Aucterra

aucterra-mcp

python

1

GitHub Stars

python

Language

6 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": {
    "japisuru-aucterra-mcp": {
      "command": "pipx",
      "args": [
        "run",
        "--spec",
        "git+https://github.com/japisuru/aucterra-mcp",
        "aucterra-mcp"
      ],
      "env": {
        "AUCTERRA_API_KEY": "your_api_key_here"
      }
    }
  }
}

You can run an MCP server that lets LLM agents access Aucterra’s document understanding services, including classification and field extraction, through a simple stdio-based MCP channel. This setup makes it easy to plug Aucterra’s capabilities into your agents and workflows with consistent MCP tooling.

How to use

You will configure your MCP client to connect to the Aucterra MCP server, then invoke the available endpoints for document classification and key-value extraction. Pass the documents you want analyzed (PDFs or images) to the tool and request the fields you need. The output will be structured JSON with the requested classifications and field values, enabling smooth downstream ingestion and decision making.

How to install

Prerequisites: ensure you have Python installed and you can run pipx. Then configure and start the MCP server as shown.

# 1) Install pipx if it is not already installed
python3 -m pip install --user pipx
python3 -m pipx ensurepath

# 2) Create the MCP configuration in your config.json or config.yaml
# Make sure you have the following mcpServers block included (see below for exact snippet).

Run the MCP server using the specified command from the configuration. The server is executed via pipx to pull the Aucterra MCP tool from its Git repository and run the package.

{
  "mcpServers": {
    "aucterra": {
      "command": "pipx",
      "args": [
        "run",
        "--spec",
        "git+https://github.com/japisuru/aucterra-mcp",
        "aucterra-mcp"
      ],
      "env": {
        "AUCTERRA_API_KEY": "your_api_key_here"
      }
    }
  }
}

Ensure your API key is set and start the MCP process according to your environment. If you are using a Google ADK integration, configure your ADK toolset to connect via stdio to this command and arguments.

Additional sections

Configuration details you will apply include the environment variable for authentication and the exact command-line invocation used to fetch and run the MCP server package.

Security: keep your API key confidential. Store it in a secure vault or environment management system and reference it in your MCP config as shown.

Available tools

Document Classification

Classify a document as a specific type (e.g., invoice, identity document) using Aucterra's classification service.

Key-Value Field Extraction

Extract structured fields from documents, including simple fields and list-based fields.