AI agents call deeplook_research to retrieve information from Deeplook without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and aggregates company information from multiple sources to generate research reports. While it provides financial analysis (bull/bear verdicts), it does not execute trades, move money, or modify data—it purely reads and synthesizes information.
From the tool's definition Server description indicates the tool 'researches any company' and 'returns structured reports' by querying 10 data sources. The tool name and server context suggest data retrieval and analysis with no modification or destructive capabilities.
Documented attack patterns abuse exactly the kind of access deeplook_research gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Deeplook, and nothing reaches the server without passing your rules. This is the rule we recommend for deeplook_research:
{
"version": "1",
"default": "deny",
"tools": {
"deeplook_research": {}
}
}deeplook_research 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.
deeplook_research. It is categorised as a Read tool in the Deeplook MCP Server, which means it retrieves data without modifying state.
Register the Deeplook MCP server in PolicyLayer and add a rule for deeplook_research: 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 Deeplook. Nothing to install.
deeplook_research 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 deeplook_research 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 deeplook_research. 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.
deeplook_research is provided by the Deeplook MCP server (osojdjd/deeplook). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Deeplook, 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.
3 Deeplook tools catalogued and risk-classified — across an index of 43,000+ MCP servers.