update_edge · Flowchart MCP: Risk & Policy

WHAT IT DOES

What update_edge does on Flowchart MCP

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

WHY IT NEEDS A POLICY

Why update_edge needs a policy

The tool modifies existing diagram edges (connections between nodes), which is a data mutation operation. This falls clearly into Write category since edge updates are reversible—they can be modified again or the diagram can be reverted. The severity is medium because misuse could corrupt flowchart logic or relationships, but the damage is localized to diagram structure and fully reversible.

From the tool's definition Tool name 'update_edge' and description 'Update an existing edge' indicate modification of existing flowchart data. This is a reversible write operation on diagram elements.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_edge Rate-limited

update_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": {
    "update_edge": {
      "limits": [
        {
          "counter": "update_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 Flowchart MCP, so you can run agents against it safely.

FAQ

Questions about update_edge

What does the update_edge tool do? +

Update an existing edge. It is categorised as a Write tool in the Flowchart MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_edge? +

Register the Flowchart MCP server in PolicyLayer and add a rule for update_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 Flowchart MCP. Nothing to install.

What risk level is update_edge? +

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

Can I rate-limit update_edge? +

Yes. Add a rate_limit block to the update_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 update_edge completely? +

Set action: deny in the PolicyLayer policy for update_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 update_edge? +

update_edge is provided by the Flowchart MCP server (zafer-liu/flowchart_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.