run_batch
Play an action on every file in a folder, or on every data set of the active document, and save the results (does what Actions panel > Batch does, by script). Folder: each .ai, .pdf, .eps or .svg file is opened, the action played, and the file left open (destination none), saved in place and clos...
This record as markdown: /tools/adobe-mcp-illustrator/run-batch.md
What run_batch does on Adobe Mcp Illustrator
AI agents invoke run_batch to trigger actions in Adobe Mcp Illustrator. 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 run_batch is rated High
run_batch triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs run_batch safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Adobe Mcp Illustrator, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_batch, this is the rule to start with:
run_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 Adobe Mcp Illustrator, apply this rule, and every run_batch call is checked against it from then on.
Questions about run_batch
Play an action on every file in a folder, or on every data set of the active document, and save the results (does what Actions panel > Batch does, by script). Folder: each .ai, .pdf, .eps or .svg file is opened, the action played, and the file left open (destination none), saved in place and closed (save_and_close), or saved as an .ai copy in destinationFolder and closed (folder; subfolders are recreated). Files already open are skipped with an error. Data sets: each data set is displayed, the action played, and with destination folder the document saved as an .ai file named by fileNaming; the document then refers to the last file saved. Save and Export steps inside the action still run as recorded. Each file runs as its own call, so a long batch does not time out. It is categorised as a Execute tool in the Adobe Mcp Illustrator MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Adobe Mcp Illustrator MCP server in PolicyLayer and add a rule for run_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 Adobe Mcp Illustrator. Nothing to install.
run_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 run_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 run_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.
run_batch is provided by the Adobe Mcp Illustrator MCP server (adobe-mcp-illustrator). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Adobe Mcp Illustrator, and thousands of servers like it.
Across the catalogue