alter-table

THE RISK

Critical Risk

Why alter-table needs a policy

The tool supports DROP column operations, which are irreversible schema changes. Even ADD and RENAME can cause data integrity issues or be disruptive, but the inclusion of DROP makes this Destructive. Misuse by an AI agent could permanently alter or destroy table structure, affecting all stored data.

From the tool's definition 'Table structure modifications (ADD/RENAME/DROP operations)' — explicitly includes DROP operations, which irreversibly remove columns from a table's schema.

Documented attack patterns abuse exactly the kind of access alter-table gives an agent:

POLICY

How to control alter-table

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Libsql, and nothing reaches the server without passing your rules. This is the rule we recommend for alter-table:

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "alter-table"
  ]
}

alter-table disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

Create a free account and register Mcp Libsql — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Mcp Libsql tools

Write create-table DDL operations for table creation with security measures Write write-query INSERT/UPDATE/DELETE operations with transaction support Read describe-table Table schema inspection with multiple output formats Read list-tables Database metadata browsing with filtering options Read read-query Execute SELECT queries with comprehensive security validation

All 6 Mcp Libsql tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in Mcp Libsql → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about alter-table

What does the alter-table tool do? +

Table structure modifications (ADD/RENAME/DROP operations). It is categorised as a Destructive tool in the Mcp Libsql MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on alter-table? +

Register the Mcp Libsql MCP server in PolicyLayer and add a rule for alter-table: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Libsql. Nothing to install.

What risk level is alter-table? +

alter-table is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit alter-table? +

Yes. Add a rate_limit block to the alter-table rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block alter-table completely? +

Set action: deny in the PolicyLayer policy for alter-table. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides alter-table? +

alter-table is provided by the Mcp Libsql MCP server (xexr/mcp-libsql). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mcp Libsql tool call.

Start from Mcp Libsql, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →