Pick the xkcd that best illustrates a document. Call this first. The server runs hybrid retrieval (BM25 + vector) over the enriched index and hands back the candidate slate plus the picker brief — same philosophy whatxkcd.com uses on its own LLM. Then you (the host LLM) read the brief, reason thr...
Risk signalsAccepts freeform code/query input (query)
Part of the Xkcdforthat server.
Free to start. No card required.
AI agents call pick_xkcd_for to retrieve information from Xkcdforthat without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though pick_xkcd_for only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"pick_xkcd_for": {}
}
}See the full Xkcdforthat policy for all 4 tools.
These attack patterns abuse exactly the kind of access pick_xkcd_for gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Pick the xkcd that best illustrates a document. Call this first. The server runs hybrid retrieval (BM25 + vector) over the enriched index and hands back the candidate slate plus the picker brief — same philosophy whatxkcd.com uses on its own LLM. Then you (the host LLM) read the brief, reason through the candidates in your own context, and either: - call render_comic(...) to draw the rich Prefab UI card (only available on hosts that support the MCP Apps UI extension), or - reply directly with the comic image and your reasoning, using the image_url and page_url already in the candidate slate. The picker_brief in the response tells you which path to take, based on what your host advertised at MCP initialize time.. It is categorised as a Read tool in the Xkcdforthat MCP Server, which means it retrieves data without modifying state.
Register the Xkcdforthat MCP server in PolicyLayer and add a rule for pick_xkcd_for: 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 Xkcdforthat. Nothing to install.
pick_xkcd_for 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 pick_xkcd_for 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 pick_xkcd_for. 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.
pick_xkcd_for is provided by the Xkcdforthat MCP server (geertjan/xkcdforthat). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Xkcdforthat tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.