pytauargus-mcp

A Model Context Protocol (MCP) server for Tau-Argus, the statistical disclosure control engine. It is the agent front-end of the D2.6 architecture: an LLM or agent (for example OpenCode) drives the stateless engine over MCP, one tool call per task, with no server-side session. The .arb batch file is the state carrier of the batch flow. It is a thin wrapper over the pytauargus Python API; it re-implements no engine behaviour. Installing it also gives you the pytauargus package.

What it does

This is the first slice: the core loop, six tools.

• tauargus_version reports the pytauargus package version and the native engine version.
• tauargus_explore inspects a microdata dataset and returns its variables with their types. It reads .parquet files directly and .asc/.rda files through the engine metadata parser.
• tauargus_build_arb writes a .arb batch file from the dataset description (wraps micro_arb).
• tauargus_run_arb runs a .arb batch and reports the table files it writes.
• tauargus_protect protects one or more tables from microdata in a single call (wraps protect). It returns per-table cell counts, status counts, the unsafe and secondary cells, and all produced file paths.
• tauargus_audit audits the suppressed cells of a table computed by a batch and returns their realised feasibility intervals.

Each tool call carries its inputs and returns a full result, so long solves can be backgrounded by the client. The server runs on the stdio transport.

Later slices add the expertise layer (MCP prompts for the standard SDC procedures, tauargus://doc/... resources pointing at the 4.1 manual and the D2.6 vision) and the plain-language reporting contract.

Install

Python 3.11 to 3.14, on the platforms the pytauargus wheel covers (macOS arm64, Linux x86_64 and aarch64, Windows x86_64). The wheel bundles the native engine and HiGHS, so no compiler, CMake, R or Java is needed.

pip install pytauargus-mcp
# or, as an extra of the engine package:
pip install "pytauargus[mcp]"

Installing it also gives you the pytauargus package and the tauargus CLI. To try it without installing anything (requires uv), run it with uvx:

uvx pytauargus-mcp

Run

tauargus-mcp   # starts the server on stdio

Point an MCP client at the console script. For OpenCode, add a tauargus server to the project or user config:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "servers": {
      "tauargus": {
        "type": "local",
        "command": ["tauargus-mcp"]
      }
    }
  }
}

With a pip install the console script is on the PATH; without one, point the command at uv instead ("command": ["uvx", "pytauargus-mcp"]).

Other MCP clients use the standard mcpServers shape:

{
  "mcpServers": {
    "tauargus": { "command": "tauargus-mcp" }
  }
}

When the server connects, the client lists its six tools. In OpenCode, /mcps shows ✓ tauargus connected.

Develop (monorepo)

cd mcp
uv sync --extra test
.venv/bin/python -m pytest tests -q

The uv sync step installs the parent package editable and builds its native extension, so the pinned engine checkout's superbuild output (engine/build/lib) must exist first. scripts/sync-venv.sh builds it if needed (it reads the sibling ../tauargus-engine checkout; point TAUARGUS_ENGINE_DIR at it for the mcp venv too, so the editable build uses the same checkout). The tests read their fixtures from $TAUARGUS_ENGINE_DIR/data (default: the sibling checkout).