Medium Risk

create_relation

Create a directed relation fromNodeId → toNodeId. relationGroupId is the relation template; list templates with get_mixins_and_relation_groups.

Part of the CoreModels server.

create_relation can modify CoreModels data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE COREMODELS →

Free to start. No card required.

AI agents use create_relation to create or modify resources in CoreModels. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call create_relation repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach CoreModels.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

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

See the full CoreModels policy for all 19 tools.

Get this rule live on your own CoreModels server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY COREMODELS →

View all 19 tools →

These attack patterns abuse exactly the kind of access create_relation gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so create_relation only ever does what you allow.

SECURE COREMODELS →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the create_relation tool do? +

Create a directed relation fromNodeId → toNodeId. relationGroupId is the relation template; list templates with get_mixins_and_relation_groups.. It is categorised as a Write tool in the CoreModels MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_relation? +

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

What risk level is create_relation? +

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

Can I rate-limit create_relation? +

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

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

create_relation is provided by the CoreModels MCP server (https://go.coremodels.io/mcp-admin). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every CoreModels tool call.

Deterministic rules across all 19 CoreModels tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.