# execute-sql

A execute tool on the Mcp Test Servers MCP server.

Agent View of the PolicyLayer registry record for `execute-sql`. HTML page: https://policylayer.com/tools/mcp-test-servers/execute-sql

## Facts

- Tool: `execute-sql`
- Server: Mcp Test Servers (`msfeldstein/mcp-test-servers`) — https://policylayer.com/tools/mcp-test-servers.md
- Homepage: https://github.com/msfeldstein/mcp-test-servers
- 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": "execute-sql",
    "arguments": {}
  }
}
```

## Why execute-sql is rated High

SQL execution is an Execute category action that can trigger external database operations with effects depending on arguments. The name provides clear evidence of this capability. Severity is critical because SQL execution can be leveraged to read, modify, or delete arbitrary data depending on database permissions and query content.

From the tool's own definition: "Tool name 'execute-sql' directly indicates execution of SQL queries. Without description, the name strongly suggests arbitrary SQL execution capability."

## Use case

AI agents invoke execute-sql to trigger actions in Mcp Test Servers. 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 Mcp Test Servers:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "execute-sql": {
      "limits": [
        {
          "counter": "execute-sql_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Mcp Test Servers (66)

- `delete-project` — Destructive — https://policylayer.com/tools/mcp-test-servers/delete-project.md
- `long-running-task` — Execute — https://policylayer.com/tools/mcp-test-servers/long-running-task.md
- `long-running-task-with-message` — Execute — https://policylayer.com/tools/mcp-test-servers/long-running-task-with-message.md
- `long-running-task-with-no-total` — Execute — https://policylayer.com/tools/mcp-test-servers/long-running-task-with-no-total.md
- `ping` — Execute — https://policylayer.com/tools/mcp-test-servers/ping.md
- `start-notification-stream` — Execute — https://policylayer.com/tools/mcp-test-servers/start-notification-stream.md
- `toggle_dynamic_tool` — Execute — https://policylayer.com/tools/mcp-test-servers/toggle-dynamic-tool.md
- `add` — Other — https://policylayer.com/tools/mcp-test-servers/add.md
- `all_types_tool` — Other — https://policylayer.com/tools/mcp-test-servers/all-types-tool.md
- `another-missing-type` — Other — https://policylayer.com/tools/mcp-test-servers/another-missing-type.md
- `bad-param` — Other — https://policylayer.com/tools/mcp-test-servers/bad-param.md
- `crash` — Other — https://policylayer.com/tools/mcp-test-servers/crash.md
- `divide` — Other — https://policylayer.com/tools/mcp-test-servers/divide.md
- `dynamic_feature` — Other — https://policylayer.com/tools/mcp-test-servers/dynamic-feature.md
- `echo` — Other — https://policylayer.com/tools/mcp-test-servers/echo.md
- `echo_structured` — Other — https://policylayer.com/tools/mcp-test-servers/echo-structured.md
- `echo_with_params` — Other — https://policylayer.com/tools/mcp-test-servers/echo-with-params.md
- `env_echo` — Other — https://policylayer.com/tools/mcp-test-servers/env-echo.md
- `fizzbuzz` — Other — https://policylayer.com/tools/mcp-test-servers/fizzbuzz.md
- `format_data` — Other — https://policylayer.com/tools/mcp-test-servers/format-data.md
- `generate_big_response` — Other — https://policylayer.com/tools/mcp-test-servers/generate-big-response.md
- `long_running_progress` — Other — https://policylayer.com/tools/mcp-test-servers/long-running-progress.md
- `many-resources-tool` — Other — https://policylayer.com/tools/mcp-test-servers/many-resources-tool.md
- `missing-type-tool` — Other — https://policylayer.com/tools/mcp-test-servers/missing-type-tool.md
- `multiply` — Other — https://policylayer.com/tools/mcp-test-servers/multiply.md
- `number-param` — Other — https://policylayer.com/tools/mcp-test-servers/number-param.md
- `optionalTool` — Other — https://policylayer.com/tools/mcp-test-servers/optionaltool.md
- `power` — Other — https://policylayer.com/tools/mcp-test-servers/power.md
- `root-echo` — Other — https://policylayer.com/tools/mcp-test-servers/root-echo.md
- `subtract` — Other — https://policylayer.com/tools/mcp-test-servers/subtract.md
- …and 36 more: https://policylayer.com/tools/mcp-test-servers.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=mcp-test-servers · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/mcp-test-servers