save_presentation

Save a presentation to a file.

SERVERCowork Bench SOURCE0717376/cowork_bench

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/cowork-bench/save-presentation.md

WHAT IT DOES

What save_presentation does on Cowork Bench

AI agents use save_presentation to create or update resources in Cowork Bench, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cowork Bench environment.

RISK

Why save_presentation is rated Medium

The tool saves/persists presentation data to storage, a reversible write operation. It does not delete existing data (would be Destructive), execute arbitrary code (would be Execute), or handle financial transactions (would be Financial). Severity is medium rather than low because file writes can have downstream consequences in a multi-task benchmark environment, and improper use could overwrite important files.

From the tool's definition Tool description states 'Save a presentation to a file', which creates or modifies a file on disk with presentation data.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs save_presentation safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Cowork Bench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For save_presentation, this is the rule to start with:

save_presentation Rate-limited

save_presentation stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "save_presentation": {
      "limits": [
        {
          "counter": "save_presentation_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Cowork Bench, apply this rule, and every save_presentation call is checked against it from then on.

FAQ

Questions about save_presentation

What does the save_presentation tool do? +

Save a presentation to a file. It is categorised as a Write tool in the Cowork Bench MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save_presentation? +

Register the Cowork Bench MCP server in PolicyLayer and add a rule for save_presentation: 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 Cowork Bench. Nothing to install.

What risk level is save_presentation? +

save_presentation is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit save_presentation? +

Yes. Add a rate_limit block to the save_presentation 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.

How do I block save_presentation completely? +

Set action: deny in the PolicyLayer policy for save_presentation. 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.

What MCP server provides save_presentation? +

save_presentation is provided by the Cowork Bench MCP server (0717376/cowork_bench). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Cowork Bench, and thousands of servers like it.

This server

All 433 Cowork Bench tools →

Across the catalogue

save_snapshot on Why Did You Render → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →