Medium Risk

upload_image_to_ipfs

Upload an image to IPFS using Pinata API.

How to control upload_image_to_ipfs ↓

What upload_image_to_ipfs does on Story SDK MCP Server

AI agents use upload_image_to_ipfs to create or update resources in Story SDK MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Story SDK MCP Server environment.

Medium Risk

Why upload_image_to_ipfs needs a policy

This tool creates and persists data (image upload to IPFS) without irreversible deletion or financial obligation. While uploads are generally persistent, they are not destructive in nature and do not involve monetary transactions.

From the tool's definition Tool name 'upload_image_to_ipfs' and description 'Upload an image to IPFS' indicate a create/store operation. The tool creates new immutable records on IPFS via Pinata API, which is a persistent write operation.

Documented attack patterns abuse exactly the kind of access upload_image_to_ipfs gives an agent:

How to control upload_image_to_ipfs

PolicyLayer is an MCP gateway — it sits between your AI agents and Story SDK MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for upload_image_to_ipfs:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "upload_image_to_ipfs": {
      "limits": [
        {
          "counter": "upload_image_to_ipfs_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

upload_image_to_ipfs 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.

  1. Create a free account and register Story SDK MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about upload_image_to_ipfs

What does the upload_image_to_ipfs tool do? +

Upload an image to IPFS using Pinata API. It is categorised as a Write tool in the Story SDK MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on upload_image_to_ipfs? +

Register the Story SDK MCP Server MCP server in PolicyLayer and add a rule for upload_image_to_ipfs: 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 Story SDK MCP Server. Nothing to install.

What risk level is upload_image_to_ipfs? +

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

Can I rate-limit upload_image_to_ipfs? +

Yes. Add a rate_limit block to the upload_image_to_ipfs 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 upload_image_to_ipfs completely? +

Set action: deny in the PolicyLayer policy for upload_image_to_ipfs. 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 upload_image_to_ipfs? +

upload_image_to_ipfs is provided by the Story SDK MCP Server MCP server (piplabs/story-mcp-hub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Story SDK MCP Server tool call.

Start from Story SDK MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

25 Story SDK MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.