Query knowledge base (hit testing). Returns: [{score, content, document_name}]
AI agents call search_dataset to retrieve information from Pulse Workflow MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query against a knowledge base/dataset and returns structured results. There is no mention of modification, deletion, execution, or financial operations. The hit testing mechanism is a standard search/retrieval pattern.
From the tool's definition Tool description states 'Query knowledge base' and 'Returns: [{score, content, document_name}]' indicating data retrieval without side effects. Named 'search_dataset' which is a passive query operation.
Attacks that exploit this kind of access
Query knowledge base (hit testing). Returns: [{score, content, document_name}]. It is categorised as a Read tool in the Pulse Workflow MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Pulse Workflow MCP Server MCP server in PolicyLayer and add a rule for search_dataset: 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 Pulse Workflow MCP Server. Nothing to install.
search_dataset 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_dataset 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_dataset. 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_dataset is provided by the Pulse Workflow MCP Server MCP server (pulse-intelligence/pulse-workflow-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 →