# mongosh-eval

Evaluates a MongoDB expression via mongosh and returns the output.

Agent View of the PolicyLayer registry record for `mongosh-eval`. HTML page: https://policylayer.com/tools/io-github-dave-london-docker/mongosh-eval

## Facts

- Tool: `mongosh-eval`
- Server: Docker (`@paretools/docker`) — https://policylayer.com/tools/io-github-dave-london-docker.md
- Install: `npx -y @paretools/docker`
- 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": "mongosh-eval",
    "arguments": {}
  }
}
```

## Why mongosh-eval is rated High

This tool executes arbitrary MongoDB expressions through the mongosh shell. An AI agent could run any MongoDB command including destructive operations (drop collections, delete documents) or data exfiltration queries. The ability to evaluate arbitrary expressions makes this Execute at minimum, with high severity due to the broad blast radius across a database.

From the tool's own definition: "'Evaluates a MongoDB expression via mongosh' — runs arbitrary code/commands against a MongoDB instance"

## Use case

AI agents invoke mongosh-eval to trigger actions in Docker. 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 Docker:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "mongosh-eval": {
      "limits": [
        {
          "counter": "mongosh-eval_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Docker (201)

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