Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

ai.dsght/public

REMOTE · WWW.DSGHT.AI · SCANNED SEP 22

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

Available components

0 this week 82 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability87
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 3072 tokens (~49/item across 62 items; 10 tools + 52 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage93
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 79% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the ai.dsght/public MCP server?

ai.dsght/public is a hosted endpoint at https://www.dsght.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · www.dsght.ai

# add to Claude Code
claude mcp add --transport http ai-dsght-public 'https://www.dsght.ai/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "ai-dsght-public": {
      "url": "https://www.dsght.ai/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "ai-dsght-public": {
      "type": "http",
      "url": "https://www.dsght.ai/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.ai-dsght-public]
url = "https://www.dsght.ai/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-dsght-public": {
      "type": "remote",
      "url": "https://www.dsght.ai/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add ai-dsght-public --url 'https://www.dsght.ai/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  ai-dsght-public:
    url: "https://www.dsght.ai/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "ai-dsght-public": {
      "Transport": "http",
      "Url": "https://www.dsght.ai/mcp"
    }
  }
}
# add to Vellum
assistant mcp add ai-dsght-public -t streamable-http -u 'https://www.dsght.ai/mcp'
// mcp.json
{
  "mcpServers": {
    "ai-dsght-public": {
      "type": "http",
      "url": "https://www.dsght.ai/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 26 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Aug 26 +1
    • Stability: 0.97 → pass security
  • 19 Aug 26 0
    • Schema quality: unverified → excellent functional
  • 18 Aug 26 0
    • Schema quality: excellent → unverified functional
    • Resource “Czech Workforce 2031 \u2014 Restructuring & Layoffs — final report” was removed functional
    • Resource “Czech Workforce 2031 \u2014 Restructuring & Layoffs — scenario matrix” was removed functional
    • Resource “Czech Workforce 2031 \u2014 Restructuring & Layoffs — structural tensions” was removed functional
    • New resource “Czech Workforce 2031 — Restructuring & Layoffs — final report” functional
    • New resource “Czech Workforce 2031 — Restructuring & Layoffs — scenario matrix” functional
    • New resource “Czech Workforce 2031 — Restructuring & Layoffs — structural tensions” functional
    • New resource “Europe''s Rearmament: Pledges vs. Reality 2026-2032 — final report” functional
    • New resource “Europe''s Rearmament: Pledges vs. Reality 2026-2032 — scenario matrix” functional
    • New resource “Europe''s Rearmament: Pledges vs. Reality 2026-2032 — structural tensions” functional
  • 17 Aug 26 0
    • Resource “Future of UX & Product Design in CEE 2026\u20132031 \u2014 Will the Profession\ — final report” was removed functional
    • Resource “Future of UX & Product Design in CEE 2026\u20132031 \u2014 Will the Profession\ — scenario matrix” was removed functional
    • Resource “Future of UX & Product Design in CEE 2026\u20132031 \u2014 Will the Profession\ — structural tensions” was removed functional
    • New resource “Future of UX & Product Design in CEE 2026–2031 — Will the Profession Survive Generative AI? — final report” functional
    • New resource “Future of UX & Product Design in CEE 2026–2031 — Will the Profession Survive Generative AI? — scenario matrix” functional
    • New resource “Future of UX & Product Design in CEE 2026–2031 — Will the Profession Survive Generative AI? — structural tensions” functional
  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 6 Aug 26 0
    • Resource “Future of UX & Product Design in CEE 2026–2031 — Will the Profession Survive Generative AI? — final report” was removed functional
    • Resource “Future of UX & Product Design in CEE 2026–2031 — Will the Profession Survive Generative AI? — scenario matrix” was removed functional
    • Resource “Future of UX & Product Design in CEE 2026–2031 — Will the Profession Survive Generative AI? — structural tensions” was removed functional
    • New resource “Future of UX & Product Design in CEE 2026\u20132031 \u2014 Will the Profession\ — final report” functional
    • New resource “Future of UX & Product Design in CEE 2026\u20132031 \u2014 Will the Profession\ — scenario matrix” functional
    • New resource “Future of UX & Product Design in CEE 2026\u20132031 \u2014 Will the Profession\ — structural tensions” functional
  • 4 Aug 26 0
    • Resource “Europe''s Rearmament: Pledges vs. Reality 2026-2032 — final report” was removed functional
    • Resource “Europe''s Rearmament: Pledges vs. Reality 2026-2032 — scenario matrix” was removed functional
    • Resource “Europe''s Rearmament: Pledges vs. Reality 2026-2032 — structural tensions” was removed functional
    • Schema quality: good → excellent functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 22 Sept 2026 · Probed https://www.dsght.ai/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=dsght.ai CN=WE1,O=Google Trust Services,C=US 29 Jul 2026 27 Oct 2026 ECDSA 256 ECDSA-SHA256 d27561e4a2884ea913cc97fee2d01a8d
SANs: dsght.ai, *.dsght.ai
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of www.dsght.ai. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
ai. present 3799 8 Verified
dsght.ai. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000; includeSubDomains; preload
content-security-policy default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval' https://www.googletagmanager.com https://www.google-analytics.com https://*.langfuse.com https://*.sentry.io https://*.ingest.sentry.io https://va.vercel-scripts.com; style-src 'self' 'unsafe-inline'; img-src 'self' data: blob: https:; font-src 'self' data:; connect-src 'self' https://gateway.dsght.ai https://*.codesandbox.io https://*.supabase.co wss://*.supabase.co https://www.google-analytics.com https://www.googletagmanager.com https://*.langfuse.com https://generativelanguage.googleapis.com https://api.openai.com https://*.sentry.io https://*.ingest.sentry.io https://vitals.vercel-insights.com https://huggingface.co https://*.huggingface.co https://*.hf.co https://cdn.jsdelivr.net; worker-src 'self' blob:; frame-src 'self' https://gateway.dsght.ai https://artifacts.dsght.ai https://*.codesandbox.io https://www.googletagmanager.com; frame-ancestors 'self'; base-uri 'self'; form-action 'self'; object-src 'none'; upgrade-insecure-requests
x-content-type-options nosniff
x-frame-options SAMEORIGIN
referrer-policy origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=(), interest-cohort=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://www.dsght.ai/mcp Verified 200
http (plaintext) http://www.dsght.ai/mcp HTTPS enforced 308 https://www.dsght.ai/mcp
MCP tools · 10 exposed · ~857 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
detect_tensions ~79

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.

NameTypeReqDescription
textstringyesStrategy / plan / memo text to analyze (plain text).

No output schema declared.

No examples provided.

extract_assumptions ~94

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.

NameTypeReqDescription
textstringyesStrategy / plan / memo text to analyze (plain text).

No output schema declared.

No examples provided.

get_country_indicator ~117

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).

NameTypeReqDescription
indicatorstringyes
jurisdictionstringyesISO code, e.g. CZ, DE, US
yearstringoptional 4-digit year, e.g. 2022

No output schema declared.

No examples provided.

get_public_report ~60

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.

NameTypeReqDescription
slugstringyesfuture-space slug from list_public_spaces

No output schema declared.

No examples provided.

get_public_scenarios ~78

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.

NameTypeReqDescription
slugstringyesfuture-space slug from list_public_spaces

No output schema declared.

No examples provided.

get_public_tensions ~77

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.

NameTypeReqDescription
slugstringyesfuture-space slug from list_public_spaces

No output schema declared.

No examples provided.

list_countries ~55

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_public_spaces ~49

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

resolve_country_claim ~168

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.

NameTypeReqDescription
directionstringyes
jurisdictionstringyesISO code, e.g. CZ, DE
resolve_bystringISO date the claim resolves by, e.g. 2022-12-31
subjectstringyese.g. "inflation", "GDP growth"
thresholdnumberyes

No output schema declared.

No examples provided.

search_spaces ~80

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.

NameTypeReqDescription
querystringyessearch terms, e.g. "open banking consent"

No output schema declared.

No examples provided.

Common questions

What is the ai.dsght/public MCP server?

ai.dsght/public is an MCP server listed in the public MCP registry as ai.dsght/public. Read-only MCP access to DSGHT.ai published foresight and country-grounded claim resolution. This page covers its hosted endpoint (https://www.dsght.ai/mcp).

Is the ai.dsght/public MCP server safe to use?

ai.dsght/public scores 82 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the ai.dsght/public MCP server expose?

ai.dsght/public exposes 10 tools: list_public_spaces, get_public_tensions, get_public_scenarios, get_public_report, search_spaces, and 5 more. Their descriptions and schemas cost roughly 857 tokens of context every time the server is loaded.

Does the ai.dsght/public MCP server require authentication?

No. We connected to ai.dsght/public without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the ai.dsght/public MCP server still maintained?

ai.dsght/public is still listed as active in the MCP registry. We last reached this channel on 22 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.