Generate format-specific instruction prompts to help LLMs create syntactically correct diagram code
AI agents call get_diagram_instructions to retrieve information from Diagram Bridge MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool generates and returns instructional content (prompts) to help users create diagram code correctly. It is purely informational — it reads from a set of format specifications and returns formatted guidance. There are no side effects, no data is created or modified in any system, no commands are executed, and no irreversible actions are taken. This is a straightforward Read operation.
From the tool's definition Tool name is 'get_diagram_instructions' and description states it 'Generate[s] format-specific instruction prompts' — this retrieves or queries pre-defined instructions/guidance for diagram syntax.
Documented attack patterns abuse exactly the kind of access get_diagram_instructions gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Diagram Bridge MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_diagram_instructions:
{
"version": "1",
"default": "deny",
"tools": {
"get_diagram_instructions": {}
}
}get_diagram_instructions is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Generate format-specific instruction prompts to help LLMs create syntactically correct diagram code. It is categorised as a Read tool in the Diagram Bridge MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Diagram Bridge MCP Server MCP server in PolicyLayer and add a rule for get_diagram_instructions: 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 Diagram Bridge MCP Server. Nothing to install.
get_diagram_instructions is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_diagram_instructions 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 get_diagram_instructions. 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.
get_diagram_instructions is provided by the Diagram Bridge MCP Server MCP server (tohachan/diagram-bridge-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Diagram Bridge MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
3 Diagram Bridge MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.