Вход

Обеспечивает только чтение доступа к опубликованным прогнозам DSGHT.ai и разрешению утверждений, привязанных к странам.

давно не проверялся схема сломана Удалённый · Streamable HTTP Без авторизации ИИ и модели public Официальный реестр · 9 просмотров

Что умеет

Обеспечивает только чтение доступа к опубликованным прогнозам DSGHT.ai и разрешению утверждений, привязанных к странам.

Перевод каталога (LLM) · показать оригинал автора

Read-only MCP access to DSGHT.ai published foresight and country-grounded claim resolution.

Подключение

Удалённый сервер: клиент обращается по адресу, код на вашей машине не запускается.

Claude Desktop

claude_desktop_config.json

Cursor

~/.cursor/mcp.json

Windsurf

~/.codeium/windsurf/mcp_config.json

Вставьте блок mcpServers в файл конфигурации своего клиента. Ключи не входят в файл: вместо SET_LOCALLY подставьте свои значения.

{
    "mcpServers": {
        "ai-dsght-public": {
            "url": "https://www.dsght.ai/mcp"
        }
    }
}

Вызов без установки — через шлюз

Агент вызывает инструменты этого сервера через https://www.n2j.ru/mcphub/mcp: hub_call_tool {"server":"ai-dsght-public","tool":"…","arguments":{…}} Ключ не нужен, но сервер N2J ограничивает частоту анонимных вызовов.

https://www.dsght.ai/mcp

Инструменты

12 схем · ≈ 1 724 условных токенов

list_public_spaces

List the DSGHT future-spaces published for public use (slug, topic, status, depth). Call this first to discover what foresight is available before fetching scenarios, tensions, or a report.

Показать схему аргументов
{
    "type": "object",
    "properties": [],
    "additionalProperties": false
}

get_public_tensions

Get the structural tensions — the load-bearing contradictions — for a published future-space. Use when the user asks what forces conflict, what could break a strategy, or what the tensions/paradoxes are in a covered domain. DSGHT surfaces contradictions rather than averaging them.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "slug"
    ],
    "properties": {
        "slug": {
            "type": "string",
            "description": "future-space slug from list_public_spaces"
        }
    },
    "additionalProperties": false
}

get_public_scenarios

Get the scenario matrix with probabilities for a published future-space. Use when the user asks how a domain (banking, energy, CEE markets, ...) might play out, what the plausible futures are, or wants to reason across scenarios instead of a single forecast.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "slug"
    ],
    "properties": {
        "slug": {
            "type": "string",
            "description": "future-space slug from list_public_spaces"
        }
    },
    "additionalProperties": false
}

get_public_report

Get the latest full foresight report (markdown) for a published future-space. Use when the user wants the detailed analysis, or a quotable, cited source on a covered topic.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "slug"
    ],
    "properties": {
        "slug": {
            "type": "string",
            "description": "future-space slug from list_public_spaces"
        }
    },
    "additionalProperties": false
}

get_public_claims

Get the evidence claims behind a published future-space that carry a cited source page (URL + quoted passage), with a census of how many claims are verified, cited or uncited. Use when you need quotable, source-backed facts on a covered topic. Uncited claims are counted, never served as sourced.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "slug"
    ],
    "properties": {
        "slug": {
            "type": "string",
            "description": "future-space slug from list_public_spaces"
        },
        "limit": {
            "type": "integer",
            "maximum": 100,
            "minimum": 1,
            "description": "page size (default 25)"
        },
        "query": {
            "type": "string",
            "description": "keywords every returned claim must contain"
        },
        "offset": {
            "type": "integer",
            "minimum": 0,
            "description": "page start (default 0)"
        },
        "status": {
            "enum": [
                "verified",
                "cited"
            ],
            "type": "string",
            "description": "only this citation status (default: both)"
        }
    },
    "additionalProperties": false
}

get_public_forecasts

Get the append-only forecast registry of a published future-space — every checkable signpost with the probability, threshold and date stated in advance, its resolution and Brier score — plus the track record. Use when the user asks how reliable DSGHT's forecasts have been, or what dated, checkable predictions a space makes.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "slug"
    ],
    "properties": {
        "slug": {
            "type": "string",
            "description": "future-space slug from list_public_spaces"
        },
        "status": {
            "enum": [
                "open",
                "resolved_true",
                "resolved_false",
                "unresolvable"
            ],
            "type": "string",
            "description": "only forecasts with this status (default: all)"
        }
    },
    "additionalProperties": false
}

search_spaces

Find the most relevant published DSGHT future-space by keyword (topic + report text, plain-text ranked, no AI). Use this to locate a space before calling get public scenarios / get public tensions / get public report when you do not already know the slug.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "query"
    ],
    "properties": {
        "query": {
            "type": "string",
            "description": "search terms, e.g. \"open banking consent\""
        }
    },
    "additionalProperties": false
}

list_countries

List the jurisdictions and macro indicators (inflation, GDP growth) available to resolve country claim and get country indicator, with per-country year coverage and source. Call this to check coverage before resolving a claim or looking up an indicator.

Показать схему аргументов
{
    "type": "object",
    "properties": [],
    "additionalProperties": false
}

get_country_indicator

Look up a country's authoritative macro indicator (inflation gdp growth) directly — deterministic, offline, cited. Use whenever you need a real macro figure instead of recalling one from memory: give the jurisdiction (CZ, DE, US, ...) and indicator, plus an optional year (omit for the full annual series).

Показать схему аргументов
{
    "type": "object",
    "required": [
        "jurisdiction",
        "indicator"
    ],
    "properties": {
        "year": {
            "type": "string",
            "description": "optional 4-digit year, e.g. 2022"
        },
        "indicator": {
            "enum": [
                "inflation",
                "gdp_growth"
            ],
            "type": "string"
        },
        "jurisdiction": {
            "type": "string",
            "description": "ISO code, e.g. CZ, DE, US"
        }
    },
    "additionalProperties": false
}

resolve_country_claim

Use this WHENEVER the user states or asks you to verify a numeric macro claim (inflation, GDP, interest rates): settle it against the claim's OWN country's authoritative series instead of answering from memory, which risks the wrong jurisdiction (e.g. U.S. CPI for a Czech claim). Binds the claim to a jurisdiction (CZ, DE, ...) and returns a cited above/below verdict. Deterministic and offline.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "subject",
        "jurisdiction",
        "direction",
        "threshold"
    ],
    "properties": {
        "subject": {
            "type": "string",
            "description": "e.g. \"inflation\", \"GDP growth\""
        },
        "direction": {
            "enum": [
                "above",
                "below"
            ],
            "type": "string"
        },
        "threshold": {
            "type": "number"
        },
        "resolve_by": {
            "type": "string",
            "description": "ISO date the claim resolves by, e.g. 2022-12-31"
        },
        "jurisdiction": {
            "type": "string",
            "description": "ISO code, e.g. CZ, DE"
        }
    },
    "additionalProperties": false
}

extract_assumptions

Use when the user pastes a strategy, plan, or memo and wants its hidden bets made explicit: extracts the falsifiable, load-bearing assumptions (dated/quantified bets + structural findings). Stateless taster — nothing is stored; the persistent per-company assumption registry with monitoring and a Brier track record is the authenticated tier.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "text"
    ],
    "properties": {
        "text": {
            "type": "string",
            "description": "Strategy / plan / memo text to analyze (plain text)."
        }
    },
    "additionalProperties": false
}

detect_tensions

Use when the user pastes strategy text and asks what is internally inconsistent: detects the structural contradictions — where the text quietly bets on two things that cannot both hold. Stateless taster; nothing is stored. DSGHT surfaces the conflict rather than smoothing it over.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "text"
    ],
    "properties": {
        "text": {
            "type": "string",
            "description": "Strategy / plan / memo text to analyze (plain text)."
        }
    },
    "additionalProperties": false
}