# describe_table

Describe the columns and types of a specific table.

Agent View of the PolicyLayer registry record for `describe_table`. HTML page: https://policylayer.com/tools/aeiyannn-postgree-mcp/describe-table

## Facts

- Tool: `describe_table`
- Server: PostgreSQL MCP Server (`aeiyannn/postgree-mcp`) — https://policylayer.com/tools/aeiyannn-postgree-mcp.md
- Homepage: https://github.com/aeiyannn/postgree-mcp
- Risk category: Read (Low risk)
- Registry record: grade C, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

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

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

## Why describe_table is rated Low

This tool only reads and returns table schema information (column names and types). It has no side effects, cannot modify or delete data, and cannot execute arbitrary code. It is clearly a Read operation with minimal security risk. The low severity reflects that schema disclosure has limited blast radius compared to query execution or data modification tools.

From the tool's own definition: "Tool description states it 'Describe the columns and types of a specific table.' This is a schema introspection operation that retrieves metadata about table structure without modifying data or executing arbitrary operations."

## Use case

AI agents call describe_table to retrieve information from PostgreSQL MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches PostgreSQL MCP Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "describe_table": {}
  }
}
```

## Other tools on PostgreSQL MCP Server (4)

- `execute` — Destructive — https://policylayer.com/tools/aeiyannn-postgree-mcp/execute.md
- `list_schemas` — Read — https://policylayer.com/tools/aeiyannn-postgree-mcp/list-schemas.md
- `list_tables` — Read — https://policylayer.com/tools/aeiyannn-postgree-mcp/list-tables.md
- `query` — Read — https://policylayer.com/tools/aeiyannn-postgree-mcp/query.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=aeiyannn-postgree-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/aeiyannn-postgree-mcp