horizon

endpoint

https://horizon.alchemylab.sh/api/mcp

protocol

streamable-http ·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 horizon live?

Yes — it answered the hub's last check (checked 36m ago). It answered 100% of checks over the last 30 days.

Is horizon free to use?

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

What tools does horizon have?

11 tools: get_related, search_news, get_china_signal, get_entity_provenance, get_topic_signal, get_regulation_updates, get_region_signal, list_sources, ….

Is horizon 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_sources reads open 3h ago

  Describe what Horizon covers: ingestion sources with their source= filter values, the regional lenses (region= / dedicated tools), and how to filter. Call this to understand the corpus before querying.

  mcp-tool

  1234

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

  arguments 4 lines copy
• get_blind_spots reads open 15h ago

  Coverage blind spots: companies, models, and people that regional press (Chinese/East-Asian, European, Latin-American) is covering while Western/global feeds are not — ranked, with per-region item counts. Answers "what is Western tech media missing right now?". Measured within Horizon's corpus: "invisible" means zero pickup in the Western feeds Horizon tracks, not a claim about all media.

  mcp-tool

  12345678910111213

  {
    "type": "object",
    "properties": {
      "days": {
        "type": "number",
        "description": "Lookback window in days (default 60, 7–180)."
      },
      "limit": {
        "type": "number",
        "description": "Max entities (default 15, cap 50)."
      }
    }
  }

  arguments 13 lines copy
• get_new_since reads open 15h ago

  Incremental poll: raw item-level AI news added since a cursor, oldest→newest, with a nextCursor for your next call — use this for "what's new since I last checked"; for the curated once-daily synthesis use get_daily_briefing. Omit cursor for the latest items plus a cursor to start polling from. Returns titles, links and topics.

  mcp-tool

  12345678910111213

  {
    "type": "object",
    "properties": {
      "limit": {
        "type": "number",
        "description": "Max items (default 25, cap 50)."
      },
      "cursor": {
        "type": "string",
        "description": "Opaque cursor from a previous call's nextCursor. Omit on the first call."
      }
    }
  }

  arguments 13 lines copy
• get_daily_briefing reads open 15h ago

  Today's AI briefing, or any past day's: top stories with their sources and corroboration labels, emerging signals, new entrants, and regulation updates. Drawn from Hacker News, Bluesky, arXiv, Hugging Face, lab blogs, tech press in the US, Europe and East Asia, and legislative sources. A curated once-daily synthesis — for raw item-level updates since your last check, use get_new_since instead. Pass a date (YYYY-MM-DD) for a past day; set top_stories_only for a shorter result.

  mcp-tool

  12345678910111213

  {
    "type": "object",
    "properties": {
      "date": {
        "type": "string",
        "description": "Optional YYYY-MM-DD for a past briefing (any date in the archive); omit for the latest briefing."
      },
      "top_stories_only": {
        "type": "boolean",
        "description": "Optional. True returns only the top stories with their sources, leaving out signals, new entrants, movers, regional highlights and regulation. Omit for the whole briefing."
      }
    }
  }

  arguments 13 lines copy
• get_related reads unknown 3h ago

  Semantic 'more like this': given an item id (from get_new_since, search_news, or the feed), returns the most similar recent items by embedding similarity. Titles, sources, similarity scores, links.

  mcp-tool

  12345678910111213141516

  {
    "type": "object",
    "required": [
      "id"
    ],
    "properties": {
      "id": {
        "type": "string",
        "description": "UUID of an item from a previous result."
      },
      "limit": {
        "type": "number",
        "description": "Max related items (default 10, cap 25)."
      }
    }
  }

  arguments 16 lines copy
• search_news reads unknown 12h ago

  Quick title search over the last 14 days of AI news: returns the top 3 matches by momentum, with links and item ids (pass one to get_related).

  mcp-tool

  123456789101112

  {
    "type": "object",
    "required": [
      "query"
    ],
    "properties": {
      "query": {
        "type": "string",
        "description": "Search terms."
      }
    }
  }

  arguments 12 lines copy
• get_china_signal reads unknown never probed

  Shortcut for get_region_signal with region "china": the current China & East-Asia AI signal (Qwen, DeepSeek, Zhipu, Moonshot, ModelScope, and more) that Western feeds often miss — ranked by momentum. Prefer get_region_signal if you may query more than one region.

  mcp-tool

  123456789

  {
    "type": "object",
    "properties": {
      "limit": {
        "type": "number",
        "description": "Max items (default 15, cap 40)."
      }
    }
  }

  arguments 9 lines copy
• get_entity_provenance reads unknown 3h ago

  For one company, model, or person: how much of the claim activity Horizon holds provenance data for is self-reported by that entity versus independently evaluated by someone else. Descriptive counts over the last 30 days — not a score, and not a judgement about whether any claim is true. Answers "is the buzz around X coming from X?".

  mcp-tool

  123456789101112

  {
    "type": "object",
    "required": [
      "entity"
    ],
    "properties": {
      "entity": {
        "type": "string",
        "description": "Entity name, e.g. 'Qwen 3.8' or 'Anthropic'."
      }
    }
  }

  arguments 12 lines copy
• get_topic_signal reads unknown never probed

  The current AI signal for a topic — recent, relevance-scored items tagged with that topic, ranked by momentum. Like get_region_signal but sliced by subject instead of geography.

  mcp-tool

  1234567891011121314151617181920212223242526

  {
    "type": "object",
    "required": [
      "topic"
    ],
    "properties": {
      "limit": {
        "type": "number",
        "description": "Max items (default 15, cap 40)."
      },
      "topic": {
        "enum": [
          "models",
          "tools",
          "use-cases",
          "regulation",
          "research",
          "funding",
          "opinion",
          "tutorial"
        ],
        "type": "string",
        "description": "Topic slug."
      }
    }
  }

  arguments 26 lines copy
• get_regulation_updates reads unknown never probed

  Current AI legislation headlines across the US Congress and federal agencies, US state legislatures, the UK Parliament, and the EU, with each item's legislative stage (proposed / committee / floor action / passed / implementation). State bills are the largest share by far; filter with jurisdiction to narrow.

  mcp-tool

  12345678910111213141516171819

  {
    "type": "object",
    "properties": {
      "limit": {
        "type": "number",
        "description": "Max headlines (default 50, cap 100)."
      },
      "jurisdiction": {
        "enum": [
          "us_federal",
          "us_state",
          "uk",
          "eu"
        ],
        "type": "string",
        "description": "Optional filter to one jurisdiction."
      }
    }
  }

  arguments 19 lines copy
• get_region_signal reads unknown never probed

  The current AI signal for a region (china, korea, japan, or eu) — recent, relevance-scored items on that region's models, labs, and analysis, ranked by momentum. Includes local-language press translated into English. The canonical regional tool; get_china_signal is a preset of this with region "china". Returns titles, sources, and links.

  mcp-tool

  12345678910111213141516171819202122

  {
    "type": "object",
    "required": [
      "region"
    ],
    "properties": {
      "limit": {
        "type": "number",
        "description": "Max items (default 15, cap 40)."
      },
      "region": {
        "enum": [
          "china",
          "korea",
          "japan",
          "eu"
        ],
        "type": "string",
        "description": "Region slug (china, korea, japan, eu)."
      }
    }
  }

  arguments 22 lines copy

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

1 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.

Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.

• artistally.alchemylab.sh artistally mcp · 4 tools