Medium Risk

store_resource

Store shared resource. Use content for <50KB, source_path for >50KB (max 500KB). With source_path: path stored in manifest, agents read file directly. For updates: include etag to prevent conflicts.

How to control store_resource ↓

What store_resource does on Brainstorm

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

Medium Risk

Why store_resource needs a policy

This tool creates or updates shared resources in a collaborative project workspace. It is reversible (resources can be deleted or updated) and does not execute code, move money, or irreversibly destroy data. The etag mechanism confirms it supports updates to existing data, placing it firmly in the Write category.

From the tool's definition Store shared resource... For updates: include etag to prevent conflicts.

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

How to control store_resource

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

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

store_resource 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 Brainstorm — 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 store_resource

What does the store_resource tool do? +

Store shared resource. Use content for <50KB, source_path for >50KB (max 500KB). With source_path: path stored in manifest, agents read file directly. For updates: include etag to prevent conflicts. It is categorised as a Write tool in the Brainstorm MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on store_resource? +

Register the Brainstorm MCP server in PolicyLayer and add a rule for store_resource: 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 Brainstorm. Nothing to install.

What risk level is store_resource? +

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

Can I rate-limit store_resource? +

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

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

store_resource is provided by the Brainstorm MCP server (theodorstorm/brainstorm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Brainstorm tool call.

Start from Brainstorm, 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.

17 Brainstorm 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.