Search through saved research data using semantic similarity.
AI agents call search_research_data to retrieve information from Kavi Research Assistant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing research data without creating, modifying, deleting, or executing any operations. It is purely informational and has no side effects on the data or system state. The low severity reflects that misuse would only expose information already stored in the research database, with no destructive or executable consequences.
From the tool's definition Tool description states it 'Search[es] through saved research data using semantic similarity' with no mention of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Search through saved research data using semantic similarity. It is categorised as a Read tool in the Kavi Research Assistant MCP Server, which means it retrieves data without modifying state.
Register the Kavi Research Assistant MCP server in PolicyLayer and add a rule for search_research_data: 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 Kavi Research Assistant. Nothing to install.
search_research_data 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 search_research_data 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 search_research_data. 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.
search_research_data is provided by the Kavi Research Assistant MCP server (machhakiran/kavi-research-assistant-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 →