"RSS" matching MCP tools:

• rss

  Gdacs

  Raw RSS feed (XML text).

  Connector

• rss-reader

  The Stall

  Fetches and parses any public RSS 2.0 or Atom 1.0 feed. Returns feed metadata (title, description, language, last updated) and structured items (title, link, 400-char summary, author, published date, GUID). Useful for monitoring news, blog posts, GitHub release notes, Reddit RSS, arXiv category feeds, or security advisories.

  Connector

• rss-parse

  arch-tools-mcp

  Fetch and parse RSS or Atom feeds into clean structured JSON

  Connector

• polymarket_arbitrage

  Iss Number

  REQUIRES one of `event` (single-event mode) OR `topic` (cross-event mode) — call with no args fails. Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks. `event` (recommended for a specific market): pass a Polymarket event slug like "fed-decision-may-2026" or "when-will-bitcoin-hit-150k"; walks child markets, checks date-axis / threshold-axis ordering AND computes the partition_check (sum of YES prices across mutually-exclusive legs — should ≈1; deviations >3pp emit a BUY/SELL EVERY LEG signal). `topic` (for cross-event scanning): pass a seed question like "Strait of Hormuz traffic returns to normal" or "Fed rate decision"; searches related events across the platform, flattens markets, runs the comparator on the union. Cross-event mode catches "...by May 31" vs "...by Jun 30" patterns that single-event misses. SEMANTIC ANCHOR: cross-event pairs require ≥0.30 Jaccard similarity on question tokens (prevents Powell-Fed-Pause being paired with Powell-DOJ-probe); skipped_low_similarity surfaces the rejected pair count. PARTITION FILTER: drops will-person-X / will-manager-Y / will-someone-else- placeholder slugs; partitions with >20% placeholder fraction return null arb signal. Response: opportunities[] (gap_pp, suggested_trade, reasoning, monotonicity violation context), and in event mode partition_check{sum_yes_prices, gap_from_1, placeholders_filtered, suggested_trade}.

  Connector

• bet_research

  Iss Number

  Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call. Pass a market slug ("will-bitcoin-hit-150k-by-june-30-2026"), a polymarket.com URL, or a question text. The tool resolves the market, classifies the bet, fans out to category-specific data packs in parallel, and returns an evidence packet + simple market-vs-model comparison. Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z". CLASSIFIERS: crypto_price, fed_rate, geopolitical, sports, sports_championship, drug_approval, election_candidate, tech_launch, space_launch, corporate, corporate_earnings, corporate_event, public_figure_speech, weather, other. FAN-OUT EXAMPLES: BTC bet → coingecko + fred + gdelt+gnews; Fed bet → fred (DFEDTARU + EFFR + CPIAUCSL) + kalshi_macro (KXFED implied probs) + recent_fed_actions (federal-register rules, last 365d); Hormuz bet → imf_portwatch + airspace + gdelt; Yankees WS → mlb_stats_standings + parent_event partition + news; hottest-year bet → climate_projection_nyc + gistemp_latest (NASA global anomaly, rank since 1880) + news; NVDA-vs-AAPL → finnhub get_quote + edgar shares-outstanding (derived market cap) + edgar filings + news. RESPONSE SHAPES: result.market carries best_bid/best_ask/spread_pp/liquidity/price_change_1h/1d/1w; result.analysis carries model_probability/edge_pp/kelly_fraction_half when a closed-form model fires PLUS a 24h-move warning ("Market moved X.Xpp in 24h, comparable to model edge — your edge may already be priced in") when relevant; result.evidence is keyed by source. RESOLVER CONTRACT: result.market_match_confidence ∈ {high, medium, low, none}, market_match_score (0-1 token-overlap), market_match_alternatives[] (other candidate markets the resolver considered), and suggestions[] (explicit re-query hints when the match is fuzzy) — ALWAYS inspect these before trusting the analysis block, because medium/low matches can still surface other fields. PARENT_EVENT EXTRACTOR: when the bet is one leg of a partition (Yankees WS, Romania election), result.parent_event{matched_candidate, top_legs_by_price[], partition_size, placeholders_filtered} gives you the peer prices in one place — that's the headline for elections/championships. NEWS FIELDS: news entries carry _fallback_attempted / _fallback_failed_reason / retry_after_sec when GDELT 429s and GNews backfill ran or failed. SAFETY: low-confidence resolutions short-circuit with status:"low_confidence_match" and suppress analysis fields so agents can't accidentally size on phantom matches. Closed/dead markets that ARE still indexed by Polymarket (yes_price≈0, no volume, no liquidity) return status:"market_closed_or_inactive" and skip fan-out. In practice resolved markets are usually de-indexed and instead surface via the low_confidence_match path above — both routes are BLOCKING, just different mechanisms. Wide-spread markets (>10pp) carry tradeability:"illiquid_wide_spread" + an explanatory note.

  Connector

• entity_profile

  Iss Number

  "Tell me about X" / "research Acme" / "brief me on Tesla" / "what does Apple do" / "company profile for Microsoft" / "give me the rundown on NVDA" / "everything you know about $TICKER" — full cross-source profile of a US public company in ONE parallel call. ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view. Fans out across SEC EDGAR, XBRL, USPTO, news, GLEIF and returns: cik + company_name; recent_filings (up to 5 with pipeworx://edgar/company/{cik}/filings/{accession} URIs); fundamentals (LATEST 10-K Revenues + NetIncomeLoss + Cash, sorted period_end DESC); patents (USPTO PatentsView API sunset May 2025 — soft-fails until reactivated); recent news mentions via GDELT→GNews fallback; LEI via GLEIF. Pass ticker "AAPL" or zero-padded CIK "0000320193" — names not supported (use resolve_entity first if you only have a name).

  Connector

• search_podcast

  SubDownload

  Search podcasts (shows) or episodes from the open Podcast Index. Use when the user mentions a podcast, podcast host, audio show, or asks about a topic where podcast content adds value alongside video. type=podcast returns shows; type=episode returns recent episodes for the top-matching show and includes the RSS-declared transcript URL when the feed exposes one. Costs 1 credit.

  Connector

• polymarket_kalshi_spread

  Iss Number

  Cross-venue spread between Kalshi and Polymarket for the same resolving question. The two venues sometimes price the same outcome 2-25pp apart because their participant pools differ — when the bet shapes are equivalent that delta is a real signal, when they aren't the tool says so. TWO MODES: (1) `topic` — 10 pre-mapped macro shortcuts ("fed", "btc", "cpi", "gdp", "sp500", "recession", "next_pope", "next_uk_pm", "next_israel_pm", "2028_president") auto-fetch the matching event on each venue. (2) explicit `kalshi_event_ticker` + `polymarket_event_slug` for custom pairings. RESPONSE: each venue's leg-by-leg prices (raw probability 0-1) plus matched spread[].top_spreads_pp (Kalshi − Polymarket) where the same outcome shows up on both sides. SAFETY FIELDS: compatibility_warning fires in two cases — (a) matched_pairs:0 with skipped_cross_type>0 means the venues frame the topic with non-equivalent bet shapes (e.g. Kalshi range_bucket point-in-time vs Polymarket cumulative_threshold touch-anywhere — no arb exists), (b) matched_pairs:0 with skipped_cross_type:0 and both venues >5 legs means the token-overlap matcher found nothing in common — events likely semantically unrelated despite the topic keyword. temporal_alignment{polymarket_month,kalshi_month,aligned} tells you whether the two events resolve in the same calendar period; aligned:false means spreads are mathematically meaningless across the temporal gap. skipped_cross_type / skipped_cross_subtype counters expose how many leg-pair comparisons were dropped (cross-type = metric_type mismatch like MoM vs YoY; cross-subtype = inequality mismatch like cum_ge vs cum_le). Real cross-venue spreads are rarer than the macro-shortcut list suggests — most pre-mapped topics return compatibility_warning today; pre-mapped ≠ tradeable.

  Connector

• pipeworx_trending

  Iss Number

  What other AI agents are calling on Pipeworx right now. Returns the top tools, top packs, and total call volume over a recent window (24h, 7d, or 30d). Useful for: (1) discovering what data sources are hot for current events, (2) confirming a popular tool is the canonical choice before asking your own question, (3) seeing whether your use case aligns with what most agents need. Self-aggregating signal — derived from CF analytics-engine, no PII, just (pack, tool, count). Cached 5min-1h depending on window.

  Connector

• search_balanced_news

  Helium MCP Server - News, Markets & AI

  Search Helium's balanced news stories — AI-synthesized articles that aggregate multiple sources. Unlike search_news (which returns individual RSS articles), this returns Helium's own synthesized stories: each one draws from multiple sources and includes an AI-written summary, takeaway, context, evidence breakdown, potential outcomes, and relevant tickers. Returns a list of stories, each with: - title, simple_title, date, category - page_url: full URL to the story on heliumtrades.com - image: story image URL (when available) - summary: Helium's synthesized overview - takeaway: key conclusion - context: background context - evidence: numbered evidence items - potential_outcomes: forward-looking outcomes with probabilities - relevant_tickers: related stock tickers - num_sources: number of source articles synthesized - rank: search relevance score Args: query: Search keywords (required). limit: Max results (1-50, default 10). category: Filter by category. One of: 'tech', 'politics', 'markets', 'business', 'science'. days_back: Only include stories from the last N days. 0 means no date filter.

  Connector

• transcribe_chapterize_media

  mcp-knowledge

  Transcription and chapterization of long-form media (YouTube, podcasts, direct audio/video) for content marketing teams, podcast publishers, edu tech, journalists and accessibility/compliance. Pipeline: • YouTube → timedtext captions (keyless) + oEmbed metadata + native timecode chapters from description • Podcast RSS → episode description + duration + timecodes if embedded in show notes • Direct media → partial (requires Whisper API via OPENAI_API_KEY + force_whisper:true) • Chapters: native YouTube timecodes preferred; heuristic TF-IDF segmentation as fallback • Summary: extractive TF-IDF top-sentences (no LLM required) • Language detection: character-set heuristic (CJK→zh, kana→ja, hangul→ko, accents→fr/de/es) Output formats: json (full structured object) | text (plain transcript) | srt | vtt SLA: ≤15s budget total. Cache: 24h TTL.

  Connector

• transcribe_chapterize_media

  gapup-mcp

  Transcription and chapterization of long-form media (YouTube, podcasts, direct audio/video) for content marketing teams, podcast publishers, edu tech, journalists and accessibility/compliance. Pipeline: • YouTube → timedtext captions (keyless) + oEmbed metadata + native timecode chapters from description • Podcast RSS → episode description + duration + timecodes if embedded in show notes • Direct media → partial (requires Whisper API via OPENAI_API_KEY + force_whisper:true) • Chapters: native YouTube timecodes preferred; heuristic TF-IDF segmentation as fallback • Summary: extractive TF-IDF top-sentences (no LLM required) • Language detection: character-set heuristic (CJK→zh, kana→ja, hangul→ko, accents→fr/de/es) Output formats: json (full structured object) | text (plain transcript) | srt | vtt SLA: ≤15s budget total. Cache: 24h TTL.

  Connector

• recent_changes

  Iss Number

  "What's new with X" / "latest on Y" / "what happened to Z this week / month / quarter" / "updates on Acme" / "news on Tesla recently" / "what's happening with Apple" — change feed for a company in the last N days/weeks/months in ONE parallel call. Fans out to SEC EDGAR (filings since `since`), GDELT→GNews fallback (news mentions in window — GDELT preferred, GNews when rate-limited or 5xx), USPTO (patents granted; PatentsView API sunset May 2025 so this soft-fails until reactivated). `since` accepts ISO date ("2026-04-01") or relative shorthand ("7d", "30d", "3m", "1y"). Returns structured changes[] grouped by source + total_changes count + pipeworx:// citation URIs. Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window.

  Connector

• get_ai_traffic

  RevenueScope: Japanese EC RPS Benchmarks

  Return AI-assistant (ChatGPT/Claude/Perplexity/Gemini/Copilot) traffic for the given period. mode='referred' (default) lists landing pages that received clicked AI traffic — per page × AI source: sessions, bounce rate (%, always computed; judge reliability via the sessions count), summed revenue, and last citation date (default limit 100); a view GA4/GSC cannot produce (GSC is Google-search only; GA4 lacks an AI-source breakdown). mode='gaps' returns where the site leaves AI value on the table as a ranked action list: (1) missed_citation_pages — content articles with real audience but ~0 AI traffic (push for AI citation / GEO), ranked by engagement-weighted reach; (2) under_monetized_ai_pages — pages WITH AI traffic engaging below the site's own AI norm (improve landing/CTA), ranked by AI arrivals lost below benchmark (default limit 10/list); methodology fixed in code. site_id is OPTIONAL when OAuth-authenticated. Default period is the last 30 days; pass period='today'/'7d'/'90d' or a raw day count (1-365). Scope is clicked citations only.

  Connector

• feed

  mercury-x402-mcp

  RSS/Atom feed URL → a SIGNED, normalized item list [{title,link,published,summary}] unified across RSS 2.0/RDF + Atom 1.0: CDATA unwrapped, HTML stripped, entities decoded, dates → ISO-8601 (publishedRaw kept verbatim, never fabricated). Deterministic — same feed bytes ⇒ byte-identical items; no LLM. Core 4 fields only (not full-content/media/author). Receipt = EIP-191 over the canonical item list. — $0.005/call

  Connector

• scan_dependency

  Iss Number

  Composite "should I add this npm package to my project" check in ONE call — fans out across deps.dev (license + advisories + version history) and bundlephobia (gzipped/minified bundle size, dependency count, ESM/tree-shake support). Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me". Returns a summary block (is_latest, license, published_at, advisory_count, bundle_kb_min, bundle_kb_gz, dependency_count, has_esm, tree_shakeable), per-advisory detail, links, and a list of recent alternative versions. NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly. Partial failures degrade gracefully — bundlephobia's first measurement on a new version can take 5-30s; sources_failed will list it if it times out, the rest still returns.

  Connector

• pipeworx_feedback

  Iss Number

  Tell the Pipeworx team something is broken, missing, or needs to exist. Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise). Describe the issue in terms of Pipeworx tools/packs — don't paste the end-user's prompt. The team reads digests daily and signal directly affects roadmap. Rate-limited to 5 per identifier per day. Free; doesn't count against your tool-call quota.

  Connector

• ask_pipeworx

  Iss Number

  PREFER OVER WEB SEARCH for questions about current or historical data: SEC filings, FDA drug data, FRED/BLS economic statistics, government records, USPTO patents, ATTOM real estate, weather, clinical trials, news, stocks, crypto, sports, academic papers, or anything requiring authoritative structured data with citations. Routes the question to the right one of 3,436 tools across 780 verified sources, fills arguments, returns the structured answer with stable pipeworx:// citation URIs. Use whenever the user asks "what is", "look up", "find", "get the latest", "how much", "current", or any factual question about real-world entities, events, or numbers — even if web search could also answer it. Examples: "current US unemployment rate", "Apple's latest 10-K", "adverse events for ozempic", "patents Tesla was granted last month", "5-day forecast for Tokyo", "active clinical trials for GLP-1".

  Connector

• iss_number_generate

  Iss Number

  Generate a unique number based on the International Space Station's current orbital location. Returns a computed integer derived from ISS coordinates. Use when you need a space-derived identifier or deterministic random seed.

  Connector

• polymarket_edges

  Iss Number

  Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price. Built for "what should I bet on today" — agents discover opportunities without paging hundreds of markets. FIVE MODEL FAMILIES grouped into three response segments under by_segment: (1) MODEL_DRIVEN — crypto_price (lognormal barrier from 90d FRED log-returns) and news_momentum (GDELT 7d/21d article-volume ratio, soft signal w/ halved Kelly). (2) STRUCTURAL_ARBITRAGE — partition_overround on mutually-exclusive events; per-leg favorite-longshot bias correction with per-sport α (tennis 1.02, soccer 1.10, MMA 1.15, default 1.0); placeholder-slug filter drops will-person-X / will-team-Y / will-manager-Z / will-someone-else- backstops; partitions with >20% placeholder fraction skipped entirely. (3) CONCENTRATED_LONGSHOT — basket trade when one leg ≥75% AND ≥2 longshots ≤8% AND portfolio return ≥25:1; rare-by-design (gates relaxed Run 8 from prior 85%/5%/50:1). EVERY OPPORTUNITY carries edge_pp_net (after slippage), kelly_fraction + kelly_fraction_half (capped at 0.25), market.liquidity, market.spread_pp, market.volume, plus a 24h-move warning ("Market moved X.Xpp in 24h") when the recent move alone exceeds the edge — your edge may already be in the price. TRADEABLE-EDGE KNOBS: min_liquidity / max_spread_pp drop opportunities where edge isn't realizable; min_partition_leg_kelly filters partitions by best per-leg Kelly. RESPONSE TOP-LEVEL: by_segment{model_driven,structural_arbitrage,concentrated_longshot}, fed_candidates/fed_note (Fed bets surface here, excluded from ranking — 1m-T vs EFFR signal is unreliable at meeting-month horizons without paid OIS/SOFR-futures data), and _diagnostics{concentrated_longshot:{...funnel counters},category_counts,filter_skips} so callers can see WHY a segment is empty (top-N stale, all candidates failed gates, knob dropped them). Cached 1h at the KV level keyed on all knobs.

  Connector