# uv-run

Runs a command in a uv-managed environment and returns structured output.

Agent View of the PolicyLayer registry record for `uv-run`. HTML page: https://policylayer.com/tools/io-github-dave-london-cargo/uv-run

## Facts

- Tool: `uv-run`
- Server: Cargo (`Dave-London/Pare`) — https://policylayer.com/tools/io-github-dave-london-cargo.md
- Homepage: https://github.com/Dave-London/pare
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

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

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

## Why uv-run is rated High

This tool executes arbitrary commands in a uv-managed Python environment. While the blast radius depends on the environment's permissions and what commands are invoked, the tool fundamentally enables code execution outside the sandbox with effects that cannot be predicted statically. Misuse could lead to system compromise, data exfiltration, or resource exhaustion.

From the tool's own definition: "Tool name 'uv-run' with description 'Runs a command in a uv-managed environment' indicates arbitrary command execution. The description explicitly states it 'runs a command', which permits execution of external operations whose effects depend on arguments."

## Use case

AI agents invoke uv-run to trigger actions in Cargo. 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 Cargo:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "uv-run": {
      "limits": [
        {
          "counter": "uv-run_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Cargo (201)

- `branch` — Destructive — https://policylayer.com/tools/io-github-dave-london-cargo/branch.md
- `clean` — Destructive — https://policylayer.com/tools/io-github-dave-london-cargo/clean.md
- `pr-close` — Destructive — https://policylayer.com/tools/io-github-dave-london-cargo/pr-close.md
- `remove` — Destructive — https://policylayer.com/tools/io-github-dave-london-cargo/remove.md
- `reset` — Destructive — https://policylayer.com/tools/io-github-dave-london-cargo/reset.md
- `secret-delete` — Destructive — https://policylayer.com/tools/io-github-dave-london-cargo/secret-delete.md
- `tag` — Destructive — https://policylayer.com/tools/io-github-dave-london-cargo/tag.md
- `variable-delete` — Destructive — https://policylayer.com/tools/io-github-dave-london-cargo/variable-delete.md
- `workspace` — Destructive — https://policylayer.com/tools/io-github-dave-london-cargo/workspace.md
- `add` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/add.md
- `add-package` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/add-package.md
- `ansible-galaxy` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/ansible-galaxy.md
- `ansible-playbook` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/ansible-playbook.md
- `api` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/api.md
- `apply` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/apply.md
- `bazel` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/bazel.md
- `biome-check` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/biome-check.md
- `bisect` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/bisect.md
- `black` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/black.md
- `build` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/build.md
- `bundle-exec` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/bundle-exec.md
- `bundle-install` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/bundle-install.md
- `check` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/check.md
- `cherry-pick` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/cherry-pick.md
- `clippy` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/clippy.md
- `cmake` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/cmake.md
- `compose-build` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/compose-build.md
- `compose-down` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/compose-down.md
- `compose-up` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/compose-up.md
- `conda` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/conda.md
- …and 171 more: https://policylayer.com/tools/io-github-dave-london-cargo.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-cargo · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-dave-london-cargo