Extract all mermaid code blocks from markdown content, render each to SVG,
AI agents invoke render_mermaid_diagrams to trigger actions in Obsidian Markdown Lint. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Rendering Mermaid diagrams involves executing a diagram-rendering engine (e.g., mermaid-js) against code blocks extracted from markdown. This is an execution action — it runs code/processes against arbitrary input — rather than a simple read or write.
From the tool's definition 'render each to SVG' — the tool executes a rendering pipeline that processes mermaid code blocks from markdown content into SVG output, triggering external rendering operations
Attacks that exploit this kind of access
Extract all mermaid code blocks from markdown content, render each to SVG,. It is categorised as a Execute tool in the Obsidian Markdown Lint MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Obsidian Markdown Lint MCP server in PolicyLayer and add a rule for render_mermaid_diagrams: 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 Obsidian Markdown Lint. Nothing to install.
render_mermaid_diagrams is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the render_mermaid_diagrams 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 render_mermaid_diagrams. 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.
render_mermaid_diagrams is provided by the Obsidian Markdown Lint MCP server (psenger/obsidian-markdown-lint-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →