whatxkcd

endpoint

https://xkcdforthat.com/mcp

protocol

http-sse ·2025-06-18

authentication

none observed

public key

none — nobody has proven they own this listing · is it yours? claim it

karma

0 · newcomer

Is whatxkcd live?

Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.

Is whatxkcd free to use?

Yes — the hub reached it with no key and no payment.

What tools does whatxkcd have?

4 tools: pick_xkcd_for, get_comic, search_comics, list_humor_types.

Is whatxkcd safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

• list_humor_types reads open 14h ago

  Return the closed vocabulary of `humor_type` tags used in the index. Useful when you want to filter or reason about candidates by humor mode rather than topic — e.g. a document about endless committees might call for `tech_culture_critique`, while one about feeling outdated might call for `interpersonal_awkwardness`.

  mcp-tool

  12345

  {
    "type": "object",
    "properties": {},
    "additionalProperties": false
  }

  arguments 5 lines copy
• pick_xkcd_for reads unknown 12h ago

  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.

  mcp-tool

  123456789101112131415161718

  {
    "type": "object",
    "required": [
      "query"
    ],
    "properties": {
      "k": {
        "type": "integer",
        "default": 15,
        "description": "Number of candidates (default 15, max 50)."
      },
      "query": {
        "type": "string",
        "description": "A short phrase capturing the document's themes, vibe, or\nconcrete topics. Examples:\n- \"the futility of design-by-committee, yet another standard\"\n- \"regex parsing, ISO 8601, time zones\"\n- \"feeling old when others don't recognize cultural references\"\nThe richer the query, the better the slate. If you have a\nlong document, summarize themes first and pass that summary."
      }
    },
    "additionalProperties": false
  }

  arguments 18 lines copy
• get_comic reads unknown 14h ago

  Fetch full details for one xkcd comic by its number. Includes everything search_comics returns plus `transcript` and `explanation` (community-written, from explainxkcd). Use this when you want richer context on a specific candidate before deciding to pick it. Always includes the required CC BY-NC attribution. The image_url is safe to hotlink — that's what xkcd's license explicitly permits.

  mcp-tool

  123456789101112

  {
    "type": "object",
    "required": [
      "num"
    ],
    "properties": {
      "num": {
        "type": "integer"
      }
    },
    "additionalProperties": false
  }

  arguments 12 lines copy
• search_comics reads unknown 14h ago

  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.

  mcp-tool

  12345678910111213141516

  {
    "type": "object",
    "required": [
      "query"
    ],
    "properties": {
      "k": {
        "type": "integer",
        "default": 15
      },
      "query": {
        "type": "string"
      }
    },
    "additionalProperties": false
  }

  arguments 16 lines copy

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.