Medium Risk

add_property

add_property

How to control add_property ↓

What add_property does on Fabric Ontology MCP Server

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

Medium Risk

Why add_property needs a policy

The tool creates or modifies ontology properties reversibly, consistent with Write operations. It is not Destructive (no irreversible deletion), not Execute (doesn't run arbitrary code), and not Financial. Severity is medium because misuse could corrupt ontology structures, but effects are scoped to metadata/schema rather than production data loss.

From the tool's definition Tool is named 'add_property' and belongs to a CRUD-capable Fabric Ontology server that 'Enables full CRUD control of Ontology items.' The sibling tools include create, add, and delete operations, indicating this tool creates or modifies ontology properties.

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

How to control add_property

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

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

add_property 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 Fabric Ontology 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 add_property

What does the add_property tool do? +

add_property. It is categorised as a Write tool in the Fabric Ontology 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 add_property? +

Register the Fabric Ontology MCP Server MCP server in PolicyLayer and add a rule for add_property: 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 Fabric Ontology MCP Server. Nothing to install.

What risk level is add_property? +

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

Can I rate-limit add_property? +

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

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

add_property is provided by the Fabric Ontology MCP Server MCP server (tmdaidevs/ontology-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Fabric Ontology MCP Server tool call.

Start from Fabric Ontology 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.

45 Fabric Ontology 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.