Critical Risk →

crow_data_write

Execute a write SQL statement (INSERT, CREATE TABLE, UPDATE, DELETE) on a user-owned database. Separate from read-only queries for safety.

How to control crow_data_write ↓

What crow_data_write does on Crow

AI agents call crow_data_write to permanently remove resources in Crow — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

Why crow_data_write needs a policy

The tool explicitly supports DELETE statements alongside INSERT, CREATE TABLE, and UPDATE. Since DELETE is irreversible data destruction, and the tool permits arbitrary SQL writes including DROP-equivalent operations, the most severe applicable category is Destructive. The blast radius is critical as an agent could delete or corrupt entire database tables/records irreversibly.

From the tool's definition Execute a write SQL statement (INSERT, CREATE TABLE, UPDATE, DELETE) on a user-owned database

Documented attack patterns abuse exactly the kind of access crow_data_write gives an agent:

How to control crow_data_write

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

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "crow_data_write"
  ]
}

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

  1. Create a free account and register Crow — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RESTRICT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about crow_data_write

What does the crow_data_write tool do? +

Execute a write SQL statement (INSERT, CREATE TABLE, UPDATE, DELETE) on a user-owned database. Separate from read-only queries for safety. It is categorised as a Destructive tool in the Crow 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 crow_data_write? +

Register the Crow MCP server in PolicyLayer and add a rule for crow_data_write: 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 Crow. Nothing to install.

What risk level is crow_data_write? +

crow_data_write 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 crow_data_write? +

Yes. Add a rate_limit block to the crow_data_write 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 crow_data_write completely? +

Set action: deny in the PolicyLayer policy for crow_data_write. 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 crow_data_write? +

crow_data_write is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Crow tool call.

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

Free to start. No card required.

576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.