# mypy

Runs mypy and returns structured type-check diagnostics (file, line, severity, message, code).

Agent View of the PolicyLayer registry record for `mypy`. HTML page: https://policylayer.com/tools/io-github-dave-london-pare-python/mypy

## Facts

- Tool: `mypy`
- Server: Python (`Dave-London/Pare`) — https://policylayer.com/tools/io-github-dave-london-pare-python.md
- Homepage: https://github.com/Dave-London/Pare
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 12
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `path` | string | no | Project root path |
| `module` | string | no | Specific module to type-check (-m MODULE) |
| `strict` | boolean | no | Enable strict mode for thorough type checking (--strict) |
| `compact` | boolean | no | Prefer compact output |
| `exclude` | string | no | Regular expression to exclude files/directories |
| `package` | string | no | Specific package to type-check (-p PACKAGE) |
| `targets` | array | no | Files or directories to check (default: ['.']) |
| `configFile` | string | no | Path to mypy config file (--config-file) |
| `pythonPath` | string | no | Python interpreter path to use (overrides executable/PATH fallback) |
| `installTypes` | boolean | no | Auto-install missing type stubs (--install-types --non-interactive) |
| `followImports` | string | no | How to handle imports (normal/silent/skip/error) |
| `noIncremental` | boolean | no | Disable incremental mode (--no-incremental) |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "mypy",
    "arguments": {}
  }
}
```

## Why mypy is rated High

The tool executes the mypy type-checker as an external process. While it is read-like in intent (reporting diagnostics), it actively runs a command/process whose effects depend on arguments. Misuse could trigger analysis of arbitrary files or paths, but blast radius is moderate since mypy itself is a read-only analysis tool with no write side effects.

From the tool's own definition: "Runs mypy and returns structured type-check diagnostics"

Risk signals: Accepts file system path (path) · High parameter count (22 properties)

## Use case

AI agents invoke mypy to trigger actions in Python. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Python:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "mypy": {
      "limits": [
        {
          "counter": "mypy_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Python (13)

- `conda` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-python/conda.md
- `pip-install` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-python/pip-install.md
- `poetry` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-python/poetry.md
- `pyenv` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-python/pyenv.md
- `pytest` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-python/pytest.md
- `ruff-check` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-python/ruff-check.md
- `uv-install` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-python/uv-install.md
- `uv-run` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-python/uv-run.md
- `black` — Read — https://policylayer.com/tools/io-github-dave-london-pare-python/black.md
- `pip-audit` — Read — https://policylayer.com/tools/io-github-dave-london-pare-python/pip-audit.md
- `pip-list` — Read — https://policylayer.com/tools/io-github-dave-london-pare-python/pip-list.md
- `pip-show` — Read — https://policylayer.com/tools/io-github-dave-london-pare-python/pip-show.md
- `ruff-format` — Read — https://policylayer.com/tools/io-github-dave-london-pare-python/ruff-format.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-dave-london-pare-python · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-dave-london-pare-python