AI agents use hf to create or update resources in Synapsis — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Synapsis environment.
The 'act=new' action creates new handoff protocol records, which modifies state in the durable team memory system. While read operations (act=get) are included, the capacity to create handoff records constitutes a Write operation. This is reversible (can be updated or overwritten) and not Destructive.
From the tool's definition Tool description specifies 'act=new (create)' capability, indicating it can create handoff records. The parameter 'act' controls whether the tool performs create or read operations.
Attacks that exploit this kind of access
Handoff: act=new (create) | act=get (read). Compact params: act, st, prio, tk, q. It is categorised as a Write tool in the Synapsis MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Synapsis MCP server in PolicyLayer and add a rule for hf: 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 Synapsis. Nothing to install.
hf 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 hf 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 hf. 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.
hf is provided by the Synapsis MCP server (teamolimpo/synapsis). 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 →