crow_data_query

Execute a read-only SQL query on a user-owned SQLite database. Only SELECT, EXPLAIN, PRAGMA, and WITH are allowed. Max 5000 rows, 10s timeout.

SERVERCrow SOURCEkh0pper/crow

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/kh0pper-crow/crow-data-query.md

WHAT IT DOES

What crow_data_query does on Crow

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

RISK

Why crow_data_query is rated Low

This tool retrieves or queries data from a SQLite database without side effects. The strict allowlist of read-only SQL operations (SELECT, EXPLAIN, PRAGMA, WITH) prevents any data modification, deletion, or execution of arbitrary code. The constraint parameters (5000 rows, 10s timeout) mitigate potential DoS concerns. Misuse would only expose existing data to an AI agent, not modify or destroy it.

From the tool's definition Tool description explicitly states 'Execute a read-only SQL query' with allowed operations limited to 'SELECT, EXPLAIN, PRAGMA, and WITH'.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs crow_data_query safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Crow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For crow_data_query, this is the rule to start with:

crow_data_query Allowed

crow_data_query is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "crow_data_query": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Crow, apply this rule, and every crow_data_query call is checked against it from then on.

FAQ

Questions about crow_data_query

What does the crow_data_query tool do? +

Execute a read-only SQL query on a user-owned SQLite database. Only SELECT, EXPLAIN, PRAGMA, and WITH are allowed. Max 5000 rows, 10s timeout. It is categorised as a Read tool in the Crow MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on crow_data_query? +

Register the Crow MCP server in PolicyLayer and add a rule for crow_data_query: 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_query? +

crow_data_query is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit crow_data_query? +

Yes. Add a rate_limit block to the crow_data_query 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_query completely? +

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

crow_data_query 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.

KEEP EXPLORING

More on Crow, and thousands of servers like it.

This server

All 587 Crow tools →

Across the catalogue

claude_query on Claude Bridge →collect_devtools_data on Percepta MCP Server → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →