Check slides for overflow. Parses Marp markdown and validates that each slide
AI agents call validate_slide to retrieve information from Marp Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool inspects slide content for structural issues (overflow validation) by parsing existing Marp markdown. It retrieves and analyzes data without side effects, modification, execution of external systems, or irreversible changes. It is a validation/analysis utility, making it a Read operation with low severity since misuse would only result in false positives/negatives in validation feedback.
From the tool's definition Tool name 'validate_slide' with description 'Check slides for overflow' and 'Parses Marp markdown and validates that each slide' - performs validation/checking without modifying or executing external operations.
Documented attack patterns abuse exactly the kind of access validate_slide gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Marp Agent, and nothing reaches the server without passing your rules. This is the rule we recommend for validate_slide:
{
"version": "1",
"default": "deny",
"tools": {
"validate_slide": {}
}
}validate_slide 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.
Check slides for overflow. Parses Marp markdown and validates that each slide. It is categorised as a Read tool in the Marp Agent MCP Server, which means it retrieves data without modifying state.
Register the Marp Agent MCP server in PolicyLayer and add a rule for validate_slide: 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 Marp Agent. Nothing to install.
validate_slide 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 validate_slide 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 validate_slide. 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.
validate_slide is provided by the Marp Agent MCP server (iwamot/marp-agent-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Marp Agent, 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 Marp Agent tools catalogued and risk-classified — across an index of 43,000+ MCP servers.