AI agents call get_conference to retrieve information from Confd without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a single conference record by identifier. It performs a read-only query with no data modification, creation, deletion, or execution capabilities. The blast radius of misuse is minimal—an agent could only access conference information it queries for, which represents standard read access to potentially sensitive but non-destructive data exposure.
From the tool's definition Tool name 'get_conference' and description 'Get a single conference by ID' indicate a retrieval operation with no side effects. The description explicitly states it returns data or a 404 error, with no mention of modification, deletion, or execution.
Attacks that exploit this kind of access
Get a single conference by ID. Returns 404 if the conference is discarded or does not exist. It is categorised as a Read tool in the Confd MCP Server, which means it retrieves data without modifying state.
Register the Confd MCP server in PolicyLayer and add a rule for get_conference: 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 Confd. Nothing to install.
get_conference 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 get_conference 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 get_conference. 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.
get_conference is provided by the Confd MCP server (mytours/confd-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 →