unifi_batch
Execute multiple UniFi tools in a single request. Each call is an object with
This record as markdown: /tools/io-github-sirkirby-unifi-access-mcp/unifi-batch.md
What unifi_batch does on UniFi Access MCP
AI agents invoke unifi_batch to trigger actions in UniFi Access MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why unifi_batch is rated High
This is an Execute tool because it orchestrates the execution of other UniFi operations in sequence or parallel. While the tool itself doesn't directly delete or move money, it can invoke any of the sibling tools (including destructive ones like access_delete_visitor) as a batch. An agent could use unifi_batch to execute multiple privileged operations atomically, amplifying the blast radius of any misuse.
From the tool's definition 'Execute multiple UniFi tools in a single request' indicates the tool runs/triggers other operations whose effects depend on what tools and arguments are batched together. The batch wrapper transforms individual tool calls into a compound operation.
Attacks that exploit this kind of access
The rule that runs unifi_batch safely
PolicyLayer is an MCP gateway: it sits between your AI agents and UniFi Access MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For unifi_batch, this is the rule to start with:
unifi_batch stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect UniFi Access MCP, apply this rule, and every unifi_batch call is checked against it from then on.
Questions about unifi_batch
Execute multiple UniFi tools in a single request. Each call is an object with. It is categorised as a Execute tool in the UniFi Access MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the UniFi Access MCP server in PolicyLayer and add a rule for unifi_batch: 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 UniFi Access MCP. Nothing to install.
unifi_batch is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the unifi_batch 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 unifi_batch. 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.
unifi_batch is provided by the UniFi Access MCP server (pypi:unifi-protect-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on UniFi Access, and thousands of servers like it.
Across the catalogue