create_architecture_edge · RoadBoard MCP: Risk & Policy

WHAT IT DOES

What create_architecture_edge does on RoadBoard

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

WHY IT NEEDS A POLICY

Why create_architecture_edge needs a policy

This tool creates/modifies project architecture metadata by adding directed edges to a graph model. It is a Write operation because: (1) it creates new data (a directed edge), (2) the operation is reversible (the edge can be deleted), and (3) the blast radius is medium—misconfigured architecture relationships could confuse project understanding but don't delete data or trigger external systems.

From the tool's definition Tool name 'create_architecture_edge' and description 'Create a directed edge between two ArchitectureNodes' indicate creation of new data structures within the project architecture graph.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_architecture_edge Rate-limited

create_architecture_edge 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": {
    "create_architecture_edge": {
      "limits": [
        {
          "counter": "create_architecture_edge_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches RoadBoard, so you can run agents against it safely.

FAQ

Questions about create_architecture_edge

What does the create_architecture_edge tool do? +

Create a directed edge between two ArchitectureNodes. Emit edgeType=. It is categorised as a Write tool in the RoadBoard 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_architecture_edge? +

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

What risk level is create_architecture_edge? +

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

Can I rate-limit create_architecture_edge? +

Yes. Add a rate_limit block to the create_architecture_edge 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_architecture_edge completely? +

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

create_architecture_edge is provided by the RoadBoard MCP server (maless88/roadboard). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.