Search past research findings across all tasks. Useful for finding relevant context from previous work.
AI agents call research_query to retrieve information from Agent Orchestration without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries historical research data to retrieve context from previous work. It performs a read-only operation—searching and retrieving information—without creating, modifying, deleting, or executing any external actions. The blast radius of misuse is minimal, as an agent cannot cause harm through reading past research findings alone.
From the tool's definition Tool name is 'research_query' and description states 'Search past research findings across all tasks.' The verb 'Search' and the action of retrieving 'past research findings' indicate data retrieval with no modification or side effects.
Documented attack patterns abuse exactly the kind of access research_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Agent Orchestration, and nothing reaches the server without passing your rules. This is the rule we recommend for research_query:
{
"version": "1",
"default": "deny",
"tools": {
"research_query": {}
}
}research_query is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search past research findings across all tasks. Useful for finding relevant context from previous work. It is categorised as a Read tool in the Agent Orchestration MCP Server, which means it retrieves data without modifying state.
Register the Agent Orchestration MCP server in PolicyLayer and add a rule for research_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 Agent Orchestration. Nothing to install.
research_query is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the research_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.
Set action: deny in the PolicyLayer policy for research_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.
research_query is provided by the Agent Orchestration MCP server (madebyaris/agent-orchestration). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Agent Orchestration, 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.
35 Agent Orchestration tools catalogued and risk-classified — across an index of 43,000+ MCP servers.