Check the status and retrieve results of a deep research task. This tool monitors the progress of an AI agent that performs comprehensive web searches, analyzes multiple sources, and synthesizes findings into detailed research reports. The tool includes a built-in 5-second delay before checking t...
AI agents call deep_researcher_check to retrieve information from Exa MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs read-only operations: checking status and retrieving already-computed results from a deep research task. It does not create, modify, delete, execute code, or commit financial transactions. The polling mechanism is a passive monitoring function. The most severe impact is information disclosure, which is low risk.
From the tool's definition Tool description explicitly states 'Check the status and retrieve results' and 'monitors the progress'—purely retrieval and polling operations with no side effects.
Attacks that exploit this kind of access
Check the status and retrieve results of a deep research task. This tool monitors the progress of an AI agent that performs comprehensive web searches, analyzes multiple sources, and synthesizes findings into detailed research reports. The tool includes a built-in 5-second delay before checking to allow processing time. IMPORTANT: You must call this tool repeatedly (poll) until the status becomes. It is categorised as a Read tool in the Exa MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Exa MCP Server MCP server in PolicyLayer and add a rule for deep_researcher_check: 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 Exa MCP Server. Nothing to install.
deep_researcher_check 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 deep_researcher_check 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 deep_researcher_check. 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.
deep_researcher_check is provided by the Exa MCP Server MCP server (zooti9er/exa-mcp-server-personal). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →