Hybrid (BM25 + vector) search over the enriched xkcd index. Returns up to k candidate comics ranked by a fusion of keyword and semantic similarity to the query. Each row contains: - num, title, alt, image_url, page_url - applicability: an LLM-written "you'd cite this when..." description - humor_...
Risk signalsAccepts freeform code/query input (query)
Part of the Xkcdforthat server.
Free to start. No card required.
AI agents call search_comics 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 search_comics 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": {
"search_comics": {}
}
}See the full Xkcdforthat policy for all 4 tools.
These attack patterns abuse exactly the kind of access search_comics 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.
Hybrid (BM25 + vector) search over the enriched xkcd index. Returns up to k candidate comics ranked by a fusion of keyword and semantic similarity to the query. Each row contains: - num, title, alt, image_url, page_url - applicability: an LLM-written "you'd cite this when..." description - humor_type: a closed-vocab tag (e.g. 'engineer_relatability') - themes: short topical tags - one_line_summary: short prose description Use this as the retrieval step when your agent picks a comic for a document. Construct a query that captures the document's themes, cultural references, or specific topics. Examples: - "the futility of design-by-committee, yet another standard" - "regex parsing edge cases, ISO 8601, time zones" - "feeling old when others don't recognize cultural references" The text channel matches Randall's exact words (titles, alt text, transcripts) for literal-keyword recall; the vector channel matches abstract themes via the LLM-written applicability prose. Both are fused so you get topical and thematic hits in one slate.. 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 search_comics: 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.
search_comics 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 search_comics 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 search_comics. 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.
search_comics 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.