Render markup text to HTML
AI agents invoke render_markup to trigger actions in Forgejo. 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 markup to HTML involves executing a server-side transformation process. While it doesn't modify stored data or delete anything, it triggers an external operation (server-side rendering) whose output depends on the input arguments. It could potentially be misused to probe server-side rendering behavior or trigger server-side processing of malicious markup.
From the tool's definition "Render markup text to HTML" — this tool processes/executes a transformation of input content
Documented attack patterns abuse exactly the kind of access render_markup gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Forgejo, and nothing reaches the server without passing your rules. This is the rule we recommend for render_markup:
{
"version": "1",
"default": "deny",
"tools": {
"render_markup": {
"limits": [
{
"counter": "render_markup_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}render_markup 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.
Free to start. No card required.
Render markup text to HTML. It is categorised as a Execute tool in the Forgejo MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Forgejo MCP server in PolicyLayer and add a rule for render_markup: 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 Forgejo. Nothing to install.
render_markup 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_markup 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_markup. 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_markup is provided by the Forgejo MCP server (sqcows/forgejo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Forgejo, 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.
103 Forgejo tools catalogued and risk-classified — across an index of 43,000+ MCP servers.