create_diagram · ContextForge MCP Gateway MCP: Risk & Policy

WHAT IT DOES

What create_diagram does on ContextForge MCP Gateway

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

WHY IT NEEDS A POLICY

Why create_diagram needs a policy

This tool creates diagram content using Mermaid syntax. Creation is reversible (diagrams can be modified or deleted by other tools), and rendering is a read-only presentation action. It does not execute arbitrary code, delete data, move funds, or trigger external system operations. The sibling tools (add_content, add_edge, add_node, etc.) support this assessment—they are all content-creation tools.

From the tool's definition Tool name 'create_diagram' and description 'Create and optionally render a Mermaid diagram' indicate creation of diagram artifacts. The verb 'create' and 'render' show that it produces new data structures without deletion or irreversible side effects.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_diagram Rate-limited

create_diagram 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_diagram": {
      "limits": [
        {
          "counter": "create_diagram_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 ContextForge MCP Gateway, so you can run agents against it safely.

FAQ

Questions about create_diagram

What does the create_diagram tool do? +

Create and optionally render a Mermaid diagram. It is categorised as a Write tool in the ContextForge MCP Gateway 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_diagram? +

Register the ContextForge MCP Gateway MCP server in PolicyLayer and add a rule for create_diagram: 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 ContextForge MCP Gateway. Nothing to install.

What risk level is create_diagram? +

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

Can I rate-limit create_diagram? +

Yes. Add a rate_limit block to the create_diagram 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_diagram completely? +

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

create_diagram is provided by the ContextForge MCP Gateway MCP server (jrmatherly/mcp-context-forge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.