Enter research mode for information gathering
AI agents call research_mode to retrieve information from MCP Shrimp Task Manager without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Research mode is designed for querying and gathering information without modifying state. It performs passive data collection activities typical of Read-category tools. The low severity reflects that information gathering alone poses minimal direct risk, even if the information gathered could later be misused by other tools on the server.
From the tool's definition The tool description states it is for 'information gathering' with no mention of side effects, modifications, or external operations. The name 'research_mode' combined with 'information gathering' indicates retrieval/query operations only.
Attacks that exploit this kind of access
Enter research mode for information gathering. It is categorised as a Read tool in the MCP Shrimp Task Manager MCP Server, which means it retrieves data without modifying state.
Register the MCP Shrimp Task Manager MCP server in PolicyLayer and add a rule for research_mode: 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 MCP Shrimp Task Manager. Nothing to install.
research_mode 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_mode 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_mode. 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_mode is provided by the MCP Shrimp Task Manager MCP server (samihalawa/gist-task-manager-mcp). 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 →