Koskamo

Horizon MCP

An MCP server that aggregates AI industry intelligence and regulation updates. It provides tools to retrieve daily briefings, track AI legislation across the US, UK, and EU, monitor regional signals (China, Korea, Japan, EU), search news, and analyze entity provenance and coverage blind spots.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Horizon MCP logo, by Alchemy LabVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by Alchemy Lab
MCP endpoint (Streamable HTTP)
https://horizon.alchemylab.sh/api/mcp
Vendor documentation

What its tools do

11 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (11)

11 of 11 have a description · 11 of 11 declare behavior hints · 10 of 10 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to horizon.alchemylab.sh ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Retrieve daily AI news briefings and regulation updates
  • Track current AI legislation across US, UK, and EU jurisdictions
  • Monitor regional AI signals for China, Korea, Japan, and EU
  • Search recent AI news and find semantically related items

Source and maintenance

Vendor evidenceRegistry 1.2.1
mcp-registry: sh.alchemylab.horizon/briefing@1.2.1Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
horizon 1.0.0
MCP protocol negotiated in check
2025-06-18
Tools
11 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Horizon — aggregated, LLM-scored AI industry intelligence (community, primary lab/media sources, research, and US/UK/EU regulation). Attribution: results are Horizon's aggregated intelligence, and each item carries its own primary source; every result's provider.citation field holds a citation crediting both. Tools: get_daily_briefing for "what happened in AI today/on <date>"; get_regulation_updates for the current state of US/UK/EU AI legislation; get_china_signal for the China & East-Asia lens (Qwen, DeepSeek, Zhipu, Moonshot, ModelScope); get_region_signal for the same lens on other regions (e.g. Europe/EU); get_topic_signal to slice by subject (models, regulation, research, funding, …); get_blind_spots for what regional press is covering that Western/global feeds are not; get_entity_provenance for how much of the claim activity around one company or model is self-reported versus independently evaluated; search_news for a quick title search (top 3 matches); get_new_since to poll new items since a cursor (each result returns the next cursor); get_related for items semantically similar to one you have; list_sources for coverage and filters.

Tools

11 advertised

get_daily_briefing
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

get_daily_briefing input schema
{
  "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."
    }
  }
}
get_daily_briefing output schema
{
  "type": "object",
  "required": [
    "briefing",
    "provider"
  ],
  "properties": {
    "briefing": {
      "type": "object",
      "required": [
        "date",
        "content"
      ],
      "properties": {
        "date": {
          "type": "string"
        },
        "content": {
          "type": "object",
          "description": "topStories, emergingSignals, newEntrants, regulation, ..."
        },
        "generatedAt": {
          "type": "string"
        }
      }
    },
    "provider": {
      "type": "object",
      "properties": {
        "url": {
          "type": "string",
          "description": "Canonical Horizon page for this result."
        },
        "name": {
          "type": "string"
        },
        "note": {
          "type": "string"
        },
        "citation": {
          "type": "string",
          "description": "Ready-to-paste citation string."
        }
      },
      "description": "Attribution: Horizon aggregated this result, and each item also names its own primary source. citation credits both; url is the Horizon page for this result."
    }
  }
}
get_daily_briefing annotations
{
  "title": "Daily AI briefing",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
get_regulation_updates
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

get_regulation_updates input schema
{
  "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."
    }
  }
}
get_regulation_updates output schema
{
  "type": "object",
  "required": [
    "items",
    "provider"
  ],
  "properties": {
    "items": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "title",
          "jurisdiction"
        ],
        "properties": {
          "stage": {
            "type": [
              "string",
              "null"
            ],
            "description": "Legislative stage as recorded from the source."
          },
          "title": {
            "type": "string"
          },
          "sourceUrl": {
            "type": [
              "string",
              "null"
            ]
          },
          "lastUpdated": {
            "type": [
              "string",
              "null"
            ]
          },
          "jurisdiction": {
            "type": "string",
            "description": "us_federal | us_state | uk | eu"
          }
        }
      }
    },
    "provider": {
      "type": "object",
      "properties": {
        "url": {
          "type": "string",
          "description": "Canonical Horizon page for this result."
        },
        "name": {
          "type": "string"
        },
        "note": {
          "type": "string"
        },
        "citation": {
          "type": "string",
          "description": "Ready-to-paste citation string."
        }
      },
      "description": "Attribution: Horizon aggregated this result, and each item also names its own primary source. citation credits both; url is the Horizon page for this result."
    }
  }
}
get_regulation_updates annotations
{
  "title": "AI regulation updates (US/UK/EU)",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
get_china_signal
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

get_china_signal input schema
{
  "type": "object",
  "properties": {
    "limit": {
      "type": "number",
      "description": "Max items (default 15, cap 40)."
    }
  }
}
get_china_signal output schema
{
  "type": "object",
  "required": [
    "items"
  ],
  "properties": {
    "items": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "title",
          "source",
          "publishedAt"
        ],
        "properties": {
          "id": {
            "type": "string",
            "description": "Item UUID — pass to get_related."
          },
          "url": {
            "type": [
              "string",
              "null"
            ]
          },
          "title": {
            "type": "string"
          },
          "source": {
            "type": "string"
          },
          "topics": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "similarity": {
            "type": "number",
            "description": "Cosine similarity (get_related only)."
          },
          "publishedAt": {
            "type": "string",
            "description": "ISO 8601 timestamp."
          }
        }
      }
    },
    "hasMore": {
      "type": "boolean",
      "description": "get_new_since: more items available now."
    },
    "provider": {
      "type": "object",
      "properties": {
        "url": {
          "type": "string",
          "description": "Canonical Horizon page for this result."
        },
        "name": {
          "type": "string"
        },
        "note": {
          "type": "string"
        },
        "citation": {
          "type": "string",
          "description": "Ready-to-paste citation string."
        }
      },
      "description": "Attribution: Horizon aggregated this result, and each item also names its own primary source. citation credits both; url is the Horizon page for this result."
    },
    "nextCursor": {
      "type": [
        "string",
        "null"
      ],
      "description": "get_new_since: pass back as cursor."
    }
  }
}
get_china_signal annotations
{
  "title": "China & East-Asia AI signal",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
get_region_signal
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

get_region_signal input schema
{
  "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)."
    }
  }
}
get_region_signal output schema
{
  "type": "object",
  "required": [
    "items"
  ],
  "properties": {
    "items": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "title",
          "source",
          "publishedAt"
        ],
        "properties": {
          "id": {
            "type": "string",
            "description": "Item UUID — pass to get_related."
          },
          "url": {
            "type": [
              "string",
              "null"
            ]
          },
          "title": {
            "type": "string"
          },
          "source": {
            "type": "string"
          },
          "topics": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "similarity": {
            "type": "number",
            "description": "Cosine similarity (get_related only)."
          },
          "publishedAt": {
            "type": "string",
            "description": "ISO 8601 timestamp."
          }
        }
      }
    },
    "hasMore": {
      "type": "boolean",
      "description": "get_new_since: more items available now."
    },
    "provider": {
      "type": "object",
      "properties": {
        "url": {
          "type": "string",
          "description": "Canonical Horizon page for this result."
        },
        "name": {
          "type": "string"
        },
        "note": {
          "type": "string"
        },
        "citation": {
          "type": "string",
          "description": "Ready-to-paste citation string."
        }
      },
      "description": "Attribution: Horizon aggregated this result, and each item also names its own primary source. citation credits both; url is the Horizon page for this result."
    },
    "nextCursor": {
      "type": [
        "string",
        "null"
      ],
      "description": "get_new_since: pass back as cursor."
    }
  }
}
get_region_signal annotations
{
  "title": "Regional AI signal",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
get_entity_provenance
Advertised by the server during the last successful anonymous check.
Advertised read-only

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?".

get_entity_provenance input schema
{
  "type": "object",
  "required": [
    "entity"
  ],
  "properties": {
    "entity": {
      "type": "string",
      "description": "Entity name, e.g. 'Qwen 3.8' or 'Anthropic'."
    }
  }
}
get_entity_provenance output schema
{
  "type": "object",
  "properties": {
    "entity": {
      "type": "string"
    },
    "provenance": {
      "type": [
        "object",
        "null"
      ],
      "properties": {
        "total": {
          "type": "number"
        },
        "qualifier": {
          "type": [
            "string",
            "null"
          ]
        },
        "independent": {
          "type": "number"
        },
        "selfReported": {
          "type": "number"
        },
        "evidenceLinked": {
          "type": "number"
        }
      },
      "description": "Null when fewer than 3 claims are held for this entity."
    }
  }
}
get_entity_provenance annotations
{
  "title": "Claim provenance for an entity",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
get_blind_spots
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

get_blind_spots input schema
{
  "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)."
    }
  }
}
get_blind_spots output schema
{
  "type": "object",
  "required": [
    "blindSpots"
  ],
  "properties": {
    "provider": {
      "type": "object",
      "properties": {
        "url": {
          "type": "string",
          "description": "Canonical Horizon page for this result."
        },
        "name": {
          "type": "string"
        },
        "note": {
          "type": "string"
        },
        "citation": {
          "type": "string",
          "description": "Ready-to-paste citation string."
        }
      },
      "description": "Attribution: Horizon aggregated this result, and each item also names its own primary source. citation credits both; url is the Horizon page for this result."
    },
    "blindSpots": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "entity",
          "regionalItems",
          "globalItems",
          "leadRegion",
          "status"
        ],
        "properties": {
          "kind": {
            "enum": [
              "company",
              "model",
              "person"
            ],
            "type": "string"
          },
          "entity": {
            "type": "string"
          },
          "status": {
            "enum": [
              "invisible",
              "under-covered"
            ],
            "type": "string",
            "description": "invisible = zero Western pickup in Horizon's corpus."
          },
          "leadRegion": {
            "enum": [
              "china",
              "korea",
              "japan",
              "eu"
            ],
            "type": "string"
          },
          "globalItems": {
            "type": "number",
            "description": "Items from Western/global press."
          },
          "regionalItems": {
            "type": "number",
            "description": "Items from regional press."
          }
        }
      }
    }
  }
}
get_blind_spots annotations
{
  "title": "Coverage blind spots",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
get_topic_signal
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

get_topic_signal input schema
{
  "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."
    }
  }
}
get_topic_signal output schema
{
  "type": "object",
  "required": [
    "items"
  ],
  "properties": {
    "items": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "title",
          "source",
          "publishedAt"
        ],
        "properties": {
          "id": {
            "type": "string",
            "description": "Item UUID — pass to get_related."
          },
          "url": {
            "type": [
              "string",
              "null"
            ]
          },
          "title": {
            "type": "string"
          },
          "source": {
            "type": "string"
          },
          "topics": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "similarity": {
            "type": "number",
            "description": "Cosine similarity (get_related only)."
          },
          "publishedAt": {
            "type": "string",
            "description": "ISO 8601 timestamp."
          }
        }
      }
    },
    "hasMore": {
      "type": "boolean",
      "description": "get_new_since: more items available now."
    },
    "provider": {
      "type": "object",
      "properties": {
        "url": {
          "type": "string",
          "description": "Canonical Horizon page for this result."
        },
        "name": {
          "type": "string"
        },
        "note": {
          "type": "string"
        },
        "citation": {
          "type": "string",
          "description": "Ready-to-paste citation string."
        }
      },
      "description": "Attribution: Horizon aggregated this result, and each item also names its own primary source. citation credits both; url is the Horizon page for this result."
    },
    "nextCursor": {
      "type": [
        "string",
        "null"
      ],
      "description": "get_new_since: pass back as cursor."
    }
  }
}
get_topic_signal annotations
{
  "title": "Topic AI signal",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
search_news
Advertised by the server during the last successful anonymous check.
Advertised read-only

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).

search_news input schema
{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "description": "Search terms."
    }
  }
}
search_news output schema
{
  "type": "object",
  "required": [
    "items"
  ],
  "properties": {
    "items": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "title",
          "source",
          "publishedAt"
        ],
        "properties": {
          "id": {
            "type": "string",
            "description": "Item UUID — pass to get_related."
          },
          "url": {
            "type": [
              "string",
              "null"
            ]
          },
          "title": {
            "type": "string"
          },
          "source": {
            "type": "string"
          },
          "topics": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "similarity": {
            "type": "number",
            "description": "Cosine similarity (get_related only)."
          },
          "publishedAt": {
            "type": "string",
            "description": "ISO 8601 timestamp."
          }
        }
      }
    },
    "hasMore": {
      "type": "boolean",
      "description": "get_new_since: more items available now."
    },
    "provider": {
      "type": "object",
      "properties": {
        "url": {
          "type": "string",
          "description": "Canonical Horizon page for this result."
        },
        "name": {
          "type": "string"
        },
        "note": {
          "type": "string"
        },
        "citation": {
          "type": "string",
          "description": "Ready-to-paste citation string."
        }
      },
      "description": "Attribution: Horizon aggregated this result, and each item also names its own primary source. citation credits both; url is the Horizon page for this result."
    },
    "nextCursor": {
      "type": [
        "string",
        "null"
      ],
      "description": "get_new_since: pass back as cursor."
    }
  }
}
search_news annotations
{
  "title": "Search AI news",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
get_new_since
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

get_new_since input schema
{
  "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."
    }
  }
}
get_new_since output schema
{
  "type": "object",
  "required": [
    "items"
  ],
  "properties": {
    "items": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "title",
          "source",
          "publishedAt"
        ],
        "properties": {
          "id": {
            "type": "string",
            "description": "Item UUID — pass to get_related."
          },
          "url": {
            "type": [
              "string",
              "null"
            ]
          },
          "title": {
            "type": "string"
          },
          "source": {
            "type": "string"
          },
          "topics": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "similarity": {
            "type": "number",
            "description": "Cosine similarity (get_related only)."
          },
          "publishedAt": {
            "type": "string",
            "description": "ISO 8601 timestamp."
          }
        }
      }
    },
    "hasMore": {
      "type": "boolean",
      "description": "get_new_since: more items available now."
    },
    "provider": {
      "type": "object",
      "properties": {
        "url": {
          "type": "string",
          "description": "Canonical Horizon page for this result."
        },
        "name": {
          "type": "string"
        },
        "note": {
          "type": "string"
        },
        "citation": {
          "type": "string",
          "description": "Ready-to-paste citation string."
        }
      },
      "description": "Attribution: Horizon aggregated this result, and each item also names its own primary source. citation credits both; url is the Horizon page for this result."
    },
    "nextCursor": {
      "type": [
        "string",
        "null"
      ],
      "description": "get_new_since: pass back as cursor."
    }
  }
}
get_new_since annotations
{
  "title": "New AI items since cursor",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
get_related
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

get_related input schema
{
  "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)."
    }
  }
}
get_related output schema
{
  "type": "object",
  "required": [
    "items"
  ],
  "properties": {
    "items": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "title",
          "source",
          "publishedAt"
        ],
        "properties": {
          "id": {
            "type": "string",
            "description": "Item UUID — pass to get_related."
          },
          "url": {
            "type": [
              "string",
              "null"
            ]
          },
          "title": {
            "type": "string"
          },
          "source": {
            "type": "string"
          },
          "topics": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "similarity": {
            "type": "number",
            "description": "Cosine similarity (get_related only)."
          },
          "publishedAt": {
            "type": "string",
            "description": "ISO 8601 timestamp."
          }
        }
      }
    },
    "hasMore": {
      "type": "boolean",
      "description": "get_new_since: more items available now."
    },
    "provider": {
      "type": "object",
      "properties": {
        "url": {
          "type": "string",
          "description": "Canonical Horizon page for this result."
        },
        "name": {
          "type": "string"
        },
        "note": {
          "type": "string"
        },
        "citation": {
          "type": "string",
          "description": "Ready-to-paste citation string."
        }
      },
      "description": "Attribution: Horizon aggregated this result, and each item also names its own primary source. citation credits both; url is the Horizon page for this result."
    },
    "nextCursor": {
      "type": [
        "string",
        "null"
      ],
      "description": "get_new_since: pass back as cursor."
    }
  }
}
get_related annotations
{
  "title": "Related AI items",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
list_sources
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

list_sources input schema
{
  "type": "object",
  "properties": {}
}
list_sources output schema
{
  "type": "object",
  "required": [
    "overview",
    "provider"
  ],
  "properties": {
    "overview": {
      "type": "string",
      "description": "The same markdown as the text block."
    },
    "provider": {
      "type": "object",
      "properties": {
        "url": {
          "type": "string",
          "description": "Canonical Horizon page for this result."
        },
        "name": {
          "type": "string"
        },
        "note": {
          "type": "string"
        },
        "citation": {
          "type": "string",
          "description": "Ready-to-paste citation string."
        }
      },
      "description": "Attribution: Horizon aggregated this result, and each item also names its own primary source. citation credits both; url is the Horizon page for this result."
    }
  }
}
list_sources annotations
{
  "title": "Coverage & sources",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
820 ms
95th percentile latency
820 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 820 ms · metadata changed · 11 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http horizon-mcp https://horizon.alchemylab.sh/api/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add horizon-mcp --url https://horizon.alchemylab.sh/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable horizon-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "horizon-mcp": {
      "url": "https://horizon.alchemylab.sh/api/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "horizon-mcp": {
      "type": "streamableHttp",
      "url": "https://horizon.alchemylab.sh/api/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start horizon-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "horizon-mcp": {
      "type": "http",
      "url": "https://horizon.alchemylab.sh/api/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http horizon-mcp https://horizon.alchemylab.sh/api/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://horizon.alchemylab.sh/api/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "horizon-mcp": {
      "serverUrl": "https://horizon.alchemylab.sh/api/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Horizon MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 5,557

Do you run Horizon MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing