AI agents use generate_diagram_from_code to create or update resources in Archy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Archy environment.
An AI agent can call generate_diagram_from_code faster than any human can review — one bad instruction and it creates or modifies resources in Archy by the hundred, each call as confident as the last.
Documented attack patterns abuse exactly the kind of access generate_diagram_from_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Archy, and nothing reaches the server without passing your rules. This is the rule we recommend for generate_diagram_from_code:
{
"version": "1",
"default": "deny",
"tools": {
"generate_diagram_from_code": {
"limits": [
{
"counter": "generate_diagram_from_code_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}generate_diagram_from_code 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.
Free to start. No card required.
Generate a Mermaid diagram from code using AI. It is categorised as a Write tool in the Archy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Archy MCP server in PolicyLayer and add a rule for generate_diagram_from_code: 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 Archy. Nothing to install.
generate_diagram_from_code is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the generate_diagram_from_code 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.
Set action: deny in the PolicyLayer policy for generate_diagram_from_code. 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.
generate_diagram_from_code is provided by the Archy MCP server (phxdev1/archy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 Archy tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
9 Archy tools catalogued and risk-classified — across an index of 42,500+ MCP servers.