ai.dsght/public

Official12 toolsLive

by dsght

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

ai.dsght/public — Model Context Protocol (MCP) Server

ai.dsght/public provides read-only MCP access to DSGHT.ai published foresight content and supports country-grounded claim resolution. The server is organized as a small toolset (10 tools) exposed via MCP, allowing developer clients to retrieve published materials without modifying or writing data.

🛠️ Key Features

Read-only MCP access
Published foresight data from DSGHT.ai
Country-grounded claim resolution
10 tools exposed via MCP

🚀 Use Cases

Retrieving published foresight material from DSGHT.ai
Resolving claims with country grounding through MCP clients

⚡ Developer Benefits

Clear separation of access mode (read-only)
Tool-based MCP integration with 10 available tools
Suitable for clients that need published-only datasets and resolution

⚠️ Limitations

Read-only access only
Scope limited to DSGHT.ai published foresight content and country-grounded claim resolution

Captured live from the server via tools/list.

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.

Parameters

No parameters.

Raw schema

{
  "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.

Parameters1

slug

string

required

future-space slug from list_public_spaces

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "future-space slug from list_public_spaces"
    }
  },
  "required": [
    "slug"
  ],
  "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.

Parameters1

slug

string

required

future-space slug from list_public_spaces

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "future-space slug from list_public_spaces"
    }
  },
  "required": [
    "slug"
  ],
  "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.

Parameters1

slug

string

required

future-space slug from list_public_spaces

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "future-space slug from list_public_spaces"
    }
  },
  "required": [
    "slug"
  ],
  "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.

Parameters5

slug	string	required	future-space slug from list_public_spaces
status	string	optional	only this citation status (default: both)
query	string	optional	keywords every returned claim must contain
limit	integer	optional	page size (default 25)
offset	integer	optional	page start (default 0)

Raw schema

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

Parameters2

slug	string	required	future-space slug from list_public_spaces
status	string	optional	only forecasts with this status (default: all)

Raw schema

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

Parameters1

query

string

required

search terms, e.g. "open banking consent"

Raw schema

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

Parameters

No parameters.

Raw schema

{
  "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).

Parameters3

jurisdiction	string	required	ISO code, e.g. CZ, DE, US
indicator	string	required
year	string	optional	optional 4-digit year, e.g. 2022

Raw schema

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

Parameters5

subject	string	required	e.g. "inflation", "GDP growth"
jurisdiction	string	required	ISO code, e.g. CZ, DE
direction	string	required
threshold	number	required
resolve_by	string	optional	ISO date the claim resolves by, e.g. 2022-12-31

Raw schema

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

Parameters1

text

string

required

Strategy / plan / memo text to analyze (plain text).

Raw schema

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "Strategy / plan / memo text to analyze (plain text)."
    }
  },
  "required": [
    "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.

Parameters1

text

string

required

Strategy / plan / memo text to analyze (plain text).

Raw schema

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

Install

Tools (12)

list_public_spacesget_public_tensionsget_public_scenariosget_public_reportget_public_claimsget_public_forecastssearch_spaceslist_countries

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://www.dsght.ai/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "public": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://www.dsght.ai/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

ai.dsght/public — Model Context Protocol (MCP) Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

list_public_spaces

get_public_tensions

get_public_scenarios

get_public_report

get_public_claims

get_public_forecasts

search_spaces

list_countries

get_country_indicator

resolve_country_claim

extract_assumptions

detect_tensions

Install

Remote endpoint

Related servers