Find sessions by a specific speaker.
AI agents call find_speaker to retrieve information from Kubecon Eu without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries conference data to return speaker sessions—a read-only retrieval operation with no side effects, state changes, or external execution. It is consistent with sibling tools like 'get_schedule' and 'get_conference_overview' that are also informational. The blast radius of misuse is minimal (unwanted query results or information disclosure about speaker sessions), warranting low severity.
From the tool's definition Tool name 'find_speaker' and description 'Find sessions by a specific speaker' indicate a search/query operation that retrieves conference schedule data without modifying or executing any actions.
Attacks that exploit this kind of access
Find sessions by a specific speaker. It is categorised as a Read tool in the Kubecon Eu MCP Server, which means it retrieves data without modifying state.
Register the Kubecon Eu MCP server in PolicyLayer and add a rule for find_speaker: 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 Kubecon Eu. Nothing to install.
find_speaker 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 find_speaker 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 find_speaker. 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.
find_speaker is provided by the Kubecon Eu MCP server (njoerd114/kubecon-eu-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 →