This record as markdown: /tools/aaronsb-texflow-mcp/render.md
What render does on TeXFlow
AI agents invoke render to trigger actions in TeXFlow. 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.
Why render is rated High
Rendering/compiling a document runs an external toolchain (e.g., pdflatex) and produces output files. This is an execution of an external process rather than a simple data write. The blast radius is medium: a misconfigured or malicious document could cause resource exhaustion or unexpected file system writes, but it doesn't inherently destroy data or move money.
From the tool's definition "Compile and export the document" — compiling triggers an external process (LaTeX/PDF renderer) and exporting writes output files; this is an operation whose effects depend on document content and arguments.
Attacks that exploit this kind of access
The rule that runs render safely
PolicyLayer is an MCP gateway: it sits between your AI agents and TeXFlow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For render, this is the rule to start with:
render stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect TeXFlow, apply this rule, and every render call is checked against it from then on.
Questions about render
Compile and export the document. It is categorised as a Execute tool in the TeXFlow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the TeXFlow MCP server in PolicyLayer and add a rule for render: 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 TeXFlow. Nothing to install.
render 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 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. 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 is provided by the TeXFlow MCP server (aaronsb/texflow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on TeXFlow, and thousands of servers like it.
Across the catalogue