grounded_query

Query Google Search via Gemini 2.5 Flash grounding.

SERVERClaude Flow SOURCEclaude-flow

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/io-github-ruvnet-claude-flow/grounded-query.md

WHAT IT DOES

What grounded_query does on Claude Flow

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

RISK

Why grounded_query is rated Low

This tool retrieves search results from Google via Gemini's grounding feature. It reads and returns information without creating, modifying, deleting, or executing anything. The blast radius of misuse is minimal—an agent could retrieve unwanted information or spam queries, but cannot alter systems or commit harmful actions.

From the tool's definition Tool name includes 'query' and description states 'Query Google Search' — a retrieval operation with no modification or execution capability. The grounding mechanism is a lookup mechanism, not an action with side effects.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs grounded_query safely

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

grounded_query Allowed

grounded_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": {
    "grounded_query": {}
  }
}

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

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

FAQ

Questions about grounded_query

What does the grounded_query tool do? +

Query Google Search via Gemini 2.5 Flash grounding. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on grounded_query? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for grounded_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 Claude Flow. Nothing to install.

What risk level is grounded_query? +

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

Can I rate-limit grounded_query? +

Yes. Add a rate_limit block to the grounded_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 grounded_query completely? +

Set action: deny in the PolicyLayer policy for grounded_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 grounded_query? +

grounded_query is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Claude Flow, and thousands of servers like it.

This server

All 496 Claude Flow tools →

Across the catalogue

claude_query on Claude Bridge → The MCP Attack Database →

Guides

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