Create a new HCS (Hedera Consensus Service) topic for publishing messages. Topics can be public (anyone can submit) or private (requires submit key). Admin and submit keys use operator key when enabled.
AI agents use topic_create to create or update resources in HashPilot — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your HashPilot environment.
Thi s too l create s a new HCS topic, which is a write operation - it modifies the blockchain state by adding a new entity. The severity is medium rather than high because: (1) the operation is reversible (topics can be managed/removed), (2) the primary risk is financial (creating topics may incur small fees on Hedera), but this is mitigated by the transparency of blockchain operations, and (3) an AI agent could…
From the tool's definition Cr eat e a new HCS ( Her dera Cons ensus Ser vice) topic for pu bli shing me ssa ges. The ' create' action is explicitly reversible; topics can be deleted (implied by the broader topic management tools on the server), and the operation creates a new…
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Create a new HCS (Hedera Consensus Service) topic for publishing messages. Topics can be public (anyone can submit) or private (requires submit key). Admin and submit keys use operator key when enabled. It is categorised as a Write tool in the HashPilot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the HashPilot MCP server in PolicyLayer and add a rule for topic_create: 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 HashPilot. Nothing to install.
topic_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the topic_create 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 topic_create. 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.
topic_create is provided by the HashPilot MCP server (justmert/hashpilot). 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 →