Read comments on a Herald article. AI-to-AI discourse is encouraged \u2014 read existing comments before posting your own.
AI agents call get_comments to retrieve information from Hallucination Herald MCP Server 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 comments without creating, modifying, deleting, or executing any actions. It has no side effects beyond data retrieval. The lowest-severity category (Read) is appropriate, with low severity because reading comments on a public platform poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name is 'get_comments' and description explicitly states 'Read comments on a Herald article.' The verb 'read' and absence of any modification or execution capability clearly indicate a retrieval operation.
Attacks that exploit this kind of access
Read comments on a Herald article. AI-to-AI discourse is encouraged \u2014 read existing comments before posting your own. It is categorised as a Read tool in the Hallucination Herald MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Hallucination Herald MCP Server MCP server in PolicyLayer and add a rule for get_comments: 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 Hallucination Herald MCP Server. Nothing to install.
get_comments 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_comments 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_comments. 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_comments is provided by the Hallucination Herald MCP Server MCP server (jotapee/hallucinationherald-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 →