MCP Knowledge

Last 30 days

Uptime

100%

Response time

253 ms typical, 253 ms slowest 5%

Last check

4 h ago

Next check

in 2 h

How to call it

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "mcp-knowledge": {
      "type": "http",
      "url": "https://mcp.gapup.io"
    }
  }
}

279 tools

• content_catalog

  Browse the Gapup gold-standard content catalogue — video games, films, TV series and music. Returns franchises with their works (title, release year). When to use this tool: an agent needs structured, audited metadata for a cultural franchise, wants to resolve a title to a canoni

• content_enrichment

  Return the enriched tag profile of a content entity — the Gapup moat. Each tag carries a facet (genre, theme, play-mode, perspective…), a confidence score, a corroboration score and its full provenance (which sources corroborated it, when). The response also carries an entity-lev

• content_discovery

  Discover content franchises within a domain. Two modes: pass `tag` for a precise taxonomy match (every game tagged 'co-op'), or pass `query` for free-text SEMANTIC search powered by pgvector embeddings — finding franchises by meaning ('dark atmospheric games about isolation') eve

• content_similar

  Find content entities similar to a given one. For embedded franchises this uses SEMANTIC vector similarity (pgvector) over the enrichment profile — surfacing entities that feel alike even when their tags differ literally. Falls back to shared enrichment-tag overlap for works or n

• content_taxonomy

  Return the enrichment taxonomy of a content domain — every tag grouped by facet (genre, theme, mood, play-mode…). When to use this tool: an agent needs the controlled vocabulary to filter, classify or query content. Input: a domain.

• content_audience_profile

  Return the audience targeting profile of a content entity — its enrichment tags reframed as audience facets with confidence, corroboration and full provenance (verifiable, sourced). The response also carries an entity-level provenance block (average confidence, data freshness). W

• content_provenance

  Audit the full data provenance of a content entity — all its enrichment tags with their extraction source, corroboration score, source list and last verification date, plus an entity-level freshness summary. Use this tool before citing or relying on enriched content data in a hig

• content_compare

  Compare the tag profiles of two content entities (franchises or works) and measure how similar they are. Returns a Jaccard similarity score, the list of shared tags, the tags unique to each entity, and a breakdown of shared tags by facet. When to use this tool: an agent needs to

• content_ranking

  Return the TOP-ranked content entities in a category, by a chosen criterion — the direct answer to superlative / decision queries: 'best video games', 'top RPGs', 'cheapest games', 'best value RPGs', 'best FPS playable right now', 'most popular music artists'. Criteria: critic_sc

• ftg_market_gap

  Return the import/production market-gap opportunities for a country — commodities where local demand outpaces local supply. Each opportunity carries the gap value (USD/year), the gap volume (tonnes/year), a 0-100 opportunity score and the potential margin. When to use this tool:

• building_enrich

  Enrich a location with European building intelligence: roof surfaces (m²), parking areas, solar-obligation status under French loi APER and loi Climat-Résilience, existing solar installations. Covers 628,000 scanned roofs and 91,800 parkings across 6 EU countries (FR, DE, IT, ES,

• web_search

  Neural and keyword web search over the live web. Returns ranked results with title, URL, publication date and author, optionally with the page text. Sub-second on repeat queries (5-minute cache).

• web_answer

  Get a direct, cited answer to a question, grounded in live web sources. Returns the answer text plus the sources it was built from. Use when you want a conclusion rather than a list of links.

• web_contents

  Extract the full text of specific URLs, with optional highlights and a summary. Use when you already know which pages you need, rather than searching for them.

• prediction_markets_search

  Search live prediction markets across Polymarket and Kalshi in one call. Returns a single normalised shape for both venues — question, implied probability (0-1), volume, end date, venue and URL — so you never have to reconcile two different price formats. Raw venue fields are pre

• polymarket_markets

  Query live Polymarket prediction markets, ranked by volume. Returns question, implied probability (0-1, derived from the outcome price), volume, liquidity, end date and URL. Optional free-text filter on the question.

• polymarket_events

  List live Polymarket events, ranked by volume. An event groups several related markets — use it to discover a topic, then polymarket_markets to price it. Returns title, description, start and end dates, and URL.

• kalshi_markets

  Query live Kalshi prediction markets (CFTC-regulated US exchange). Returns question, implied probability (0-1, derived from the yes bid/ask mid), volume, open interest, close time and URL. Optional free-text filter on the question.

• ftg_production_methods

  Return the production methods for a commodity — each with a description, ordered process steps, pros/cons and a popularity rank. Methods are commodity-canonical: one curated set per commodity, reusable across every country. When to use this tool: an agent evaluates HOW a commodit

• ftg_sourcing_buyers

  Return verified local buyers in a country — companies sourcing a given commodity, with buyer type, city, website, annual volume range and certification requirements. When to use this tool: an agent builds a sourcing or export shortlist, or needs real B2B demand contacts in a mark

• ftg_opportunity_scout

  Rank the best countries for a given commodity — where the market gap, opportunity score and potential margin are highest. Cross-country scouting. When to use this tool: an agent has a commodity and needs to know WHERE to sell, export to or set up local production. Input: a commod

• ftg_business_plan

  Return the business plan for a market-gap opportunity — direct-trade or local-production, with CAPEX, OPEX, ROI, payback period, automation level and the full plan. Cache-first: returns the stored plan when available, otherwise reports that generation is required (the FTG platfor

• ftg_production_economics

  Return production cost benchmarks (CAPEX/OPEX per unit, value ranges, scenarios, quality tiers) and agronomic yields (t/ha, cycles per year) for a commodity. When to use this tool: an agent sizes the economics of producing a commodity. Input: a commodity, with an optional country

• ftg_investor_directory

  Return investors from the FTG directory — VC, PE and impact funds with type, firm, website, ticket-size range, sectors and stages of interest. When to use this tool: an agent builds a fundraising shortlist. Input: optional country and limit.

• ftg_country_regulations

  Return import, trade and production regulations for a country — category, title, summary and source. When to use this tool: an agent checks regulatory or compliance requirements before trading or producing in a market. Input: a country, with an optional category.

• ftg_business_ideas

  Return vetted, automation-scored business ideas from the FTG idea bank — each with an autonomy score, monetization model and conservative/median/optimistic MRR projections. When to use this tool: an agent or founder wants ranked, buildable business ideas. Input: optional category

• ftg_country_study

  Return the in-depth FTG country study — multi-part structured analysis of a country's trade and production landscape. When to use this tool: an agent needs deep country context before a sourcing, export or investment decision. Input: a country.

• ftg_seller_catalog

  Return seller catalogues registered on FTG — exporters and producers with their commodity, monthly capacity, certifications and target export markets. When to use this tool: an agent builds a supplier or sourcing shortlist. Input: optional seller country and commodity.

• competitor_intel

  LLM-narrated competitive-intelligence BRIEFING — for human consumption (board meeting, pitch prep). Pair tool: `competitive_deep_dive` for raw structured multi-source data (agent-shaped JSON). Returns: recent competitor moves with severity (critical/high/medium/low), prioritised

• trend_watcher

  Monitor emerging trends, regulatory shifts and adoption signals for a given market sector. Returns 5-12 trend cards, each with a momentum score (rising/stable/declining), a 3-month and 12-month outlook, opportunity windows, and recommended actions. When to use this tool: the user

• partnership_synergies

  Identify and rank strategic partnership opportunities for a company. Returns 5-12 high-fit partnership targets, each scored on revenue lift, time-to-impact, integration complexity and regulatory risk, with a rationale and a recommended first-step outreach playbook. When to use th

• pitch_deck_storyline

  Build a complete investor pitch-deck storyline for a company. Returns an 8-20 slide narrative tailored to the target audience (seed-vc / series-a-vc / growth-vc / strategic / bank / grant) — each slide carrying a title, key points, a speaker note and a visual hint — plus a Q&A ba

• carbon_footprint_calculator

  Calculate a company's greenhouse-gas footprint under the GHG Protocol (Scope 1 + 2 + 3, in tCO2eq, tier-2 accuracy ±20%). Returns the emissions breakdown, hotspot identification, 5-8 reduction levers each with capex and payback, an SBTi-aligned reduction trajectory over 5-25 year

• market_research_brief

  Generate a structured, sourced market research brief on any market, sector or industry. Returns a machine-readable note with six sections: an executive overview, a market-size estimate (with assumptions and sources — no invented figures), key players, demand & technology trends,

• competitive_deep_dive

  Gold-standard competitive deep dive — STRUCTURED multi-source data (no LLM narrative). Pair tool: `competitor_intel` for LLM-narrated board briefing + slide script. Aggregates Wikipedia, Yahoo Finance, SEC EDGAR, Wayback Machine, DuckDuckGo, HackerNews, domain scraping — all keyl

• competitive_deep_dive_async

  Async variant of competitive_deep_dive. Returns immediately (<200ms) with a job_id. The research runs in the background (p50≈25s, p95≈30s for depth=medium). Poll the result with competitive_deep_dive_result(job_id) after the eta_seconds hint. Use this instead of competitive_deep_

• competitive_deep_dive_result

  Poll the result of a competitive_deep_dive_async job. Returns status=pending while running, status=completed with the full report once done, status=failed on error, or status=not_found if the job_id is unknown or expired (TTL 24h). Call this after the eta_seconds hint returned by

• kyc_screener_batch

  Async batch variant of kyc_screener. Accepts 1-100 names and returns immediately (<300ms) with a job_id. The screening runs in the background (up to 10 parallel KYC calls). Poll the result with kyc_screener_batch_result(job_id) after the eta_seconds hint. Each entry can specify n

• kyc_screener_batch_result

  Poll the result of a kyc_screener_batch job. Returns status=pending while running, status=completed with the full array of KYC results once done, status=failed on error, or status=not_found if the job_id is unknown or expired (TTL 24h). Call this after the eta_seconds hint return

• ai_governance_full_report_async

  Audit EU AI Act complet (Règlement UE 2024/1689) — implémentation native audit-grade. Classifie le système IA selon les 4 tiers de risque (unacceptable/high_risk/limited_risk/minimal_risk/gpai) sur la base de l'Annexe III et de l'Article 5. Produit : (1) classification tier + jus

Security scan

• No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks