gbrain_search

Keyword search across the wiki brain (FTS5). Faster than gbrain_query

SERVERAgent Store SOURCEchrisluersen/agent-store

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade D, identity unverified Pull the record →

This record as markdown: /tools/agent-store/gbrain-search.md

WHAT IT DOES

What gbrain_search does on Agent Store

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

RISK

Why gbrain_search is rated Low

This tool retrieves data using full-text search (FTS5) without side effects. It is a read-only operation that returns results from an indexed search index. No data is created, modified, deleted, or executed. The only risk is potential information disclosure if the search index contains sensitive data, hence low severity.

From the tool's definition Tool performs 'Keyword search across the wiki brain (FTS5)' — a query operation with no modification or execution capability. The description explicitly indicates it retrieves information ('search') rather than modifying or executing code.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs gbrain_search safely

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

gbrain_search Allowed

gbrain_search 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": {
    "gbrain_search": {}
  }
}

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

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

FAQ

Questions about gbrain_search

What does the gbrain_search tool do? +

Keyword search across the wiki brain (FTS5). Faster than gbrain_query. It is categorised as a Read tool in the Agent Store MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on gbrain_search? +

Register the Agent Store MCP server in PolicyLayer and add a rule for gbrain_search: 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 Agent Store. Nothing to install.

What risk level is gbrain_search? +

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

Can I rate-limit gbrain_search? +

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

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

gbrain_search is provided by the Agent Store MCP server (chrisluersen/agent-store). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Agent Store, and thousands of servers like it.

This server

All 19 Agent Store tools →

Across the catalogue

search_torrents on M-Team MCP Server →aiva_search_customers on AIVA MCP Server →search_channel on YouTube MCP Server →search_circuits on 0gzk → The MCP Attack Database →

Guides

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