Today's trending ML/AI papers (or a given day's), ranked by community upvotes, via Hugging Face Papers. Use for "what are the hot AI papers", "trending ML research", "top papers this week".
ConnectorNo auth
745,212 tools. Updated 2026-11-05 06:09
"Automated workflow for collecting, summarizing and translating trending research papers" matching MCP tools:
- Get trending or searched AI/ML research papers from HuggingFace Papers. Returns trending papers for a given date or search results by keyword.ConnectorNo auth
- Get trending or searched AI/ML research papers from HuggingFace Papers. Returns trending papers for a given date or search results by keyword.ConnectorNo auth
- Maps to GET /pools. Discovers liquidity pools across supported AMMs and chains, returning id, poolId, symbol, underlyingTokens (token addresses), fee tier, protocol, dexKind, APY, apyBase (fee-only APY excluding reward emissions), TVL (USD), 24h/7d volume (USD), stablecoin flags, and hooksAddress (custom hook contract for Uniswap V4 / PancakeSwap Infinity pools; null when the pool has no hook — hooks can add custom fees or transfer restrictions). KEY PARAMETERS: Use `trending: true` to get only pools currently trending, optionally with `timeframe` ("5m", "1h", "6h", "24h") to select the ranking window — default is 5m. Trending results include `feeAprEstimate`: fee APR (%) annualized from the selected timeframe's volume window over the pool reserve (null outside trending mode or when the fee tier is unknown). NOTE: `feeAprEstimate` extrapolates a short window to a year — for short timeframes on hot pools it can be extreme and short-lived; the `apy` field is the stable 24h-based metric. MOMENTUM SIGNAL (1h/6h/24h windows, powered by on-chain DEX trade data): each trending pool carries `momentumSignal` — "entry" (volume accelerating with healthy LP flow — a pool worth entering), "watch" (in the ranking but not yet actionable), or "exit" (dying volume or LPs leaving). Supporting fields: `momentumScore` (composite acceleration x size x flow quality), `momentumRatioH1/H6/H24` (volume vs the previous equal window), `momentumTakersH6` (unique traders 6h), `lpMintsH6/lpBurnsH6` and `lpNetFlowH6` (inflow/outflow/flat — are LPs adding or pulling liquidity). The 5m window carries the signal as HOURLY CONTEXT (last hourly cycle, not the last 5 minutes), since 5m is real-time GeckoTerminal data. Each pool also carries `suggestedRangePct`: a suggested concentrated-liquidity range (± percent) balancing fee density against time-in-range — ~0.5% for stable pairs, tens of percent for volatile/memecoin pairs — pass it to zap_into_lp_position. To ENTER the hottest profitable pool: `trending: true, timeframe: "6h", signal: "entry", sortBy: "signal", sortOrder: "desc"` returns entry-signal pools ranked by APR. (Use timeframe "6h" for sustained traction / LP-yield strategies, "1h" for faster reaction.) To check whether to EXIT, read `momentumSignal` on list_user_lp_positions instead. Use `hookless: true` to exclude pools with a custom hook contract. Use `sortBy` ("apy", "tvl", "volume1d", "volume7d", "signal") with `sortOrder` to control ranking — default is tvl desc. Use `topPerVenue` to limit to top N pools per DEX by APY. Supports filtering by protocol/DEX, tokens, pool type, stablecoin status, and free-text search, with pagination. Required upstream step before zap_into_lp_position. IMPORTANT: The response contains two ID fields — `poolId` (string) must be passed AS-IS to zap_into_lp_position and zap_out_of_lp_position (do NOT construct or modify it), and `id` (number) is used only for analyze_pool.ConnectorNo auth
- Analyze a website URL for WCAG 2.1 Level A accessibility issues. Automated static HTML analysis covering approximately 30-40% of WCAG 2.1 Level A criteria. Checks include: image alt text, form labels, heading hierarchy, page title, html lang, empty links/buttons, ARIA labels, duplicate IDs, skip navigation, table headers, landmarks, viewport zoom, autoplay media, and tabindex ordering. Manual testing is required for full WCAG compliance assessment. Results are cached for fast subsequent lookups. Rate limited to 1 request per minute per domain. Args: url: The website URL to analyze (e.g., "https://example.com"). Returns: WCAG analysis with: - url: The analyzed URL - score: Accessibility score (0-100) - grade: Letter grade (A-F) - issues: Categorized issues (critical, warnings, info) - meta: Extracted accessibility metadata - recommendations: Prioritized improvements - coverage_note: Disclaimer about automated coverage - cached: Whether result was from cacheConnectorNo auth
- Maps to GET /pools. Discovers liquidity pools across supported AMMs and chains, returning id, poolId, symbol, underlyingTokens (token addresses), fee tier, protocol, dexKind, APY, apyBase (fee-only APY excluding reward emissions), TVL (USD), 24h/7d volume (USD), stablecoin flags, and hooksAddress (custom hook contract for Uniswap V4 / PancakeSwap Infinity pools; null when the pool has no hook — hooks can add custom fees or transfer restrictions). KEY PARAMETERS: Use `trending: true` to get only pools currently trending, optionally with `timeframe` ("5m", "1h", "6h", "24h") to select the ranking window — default is 5m. Trending results include `feeAprEstimate`: fee APR (%) annualized from the selected timeframe's volume window over the pool reserve (null outside trending mode or when the fee tier is unknown). NOTE: `feeAprEstimate` extrapolates a short window to a year — for short timeframes on hot pools it can be extreme and short-lived; the `apy` field is the stable 24h-based metric. MOMENTUM SIGNAL (1h/6h/24h windows, powered by on-chain DEX trade data): each trending pool carries `momentumSignal` — "entry" (volume accelerating with healthy LP flow — a pool worth entering), "watch" (in the ranking but not yet actionable), or "exit" (dying volume or LPs leaving). Supporting fields: `momentumScore` (composite acceleration x size x flow quality), `momentumRatioH1/H6/H24` (volume vs the previous equal window), `momentumTakersH6` (unique traders 6h), `lpMintsH6/lpBurnsH6` and `lpNetFlowH6` (inflow/outflow/flat — are LPs adding or pulling liquidity). The 5m window carries the signal as HOURLY CONTEXT (last hourly cycle, not the last 5 minutes), since 5m is real-time GeckoTerminal data. Each pool also carries `suggestedRangePct`: a suggested concentrated-liquidity range (± percent) balancing fee density against time-in-range — ~0.5% for stable pairs, tens of percent for volatile/memecoin pairs — pass it to zap_into_lp_position. To ENTER the hottest profitable pool: `trending: true, timeframe: "6h", signal: "entry", sortBy: "signal", sortOrder: "desc"` returns entry-signal pools ranked by APR. (Use timeframe "6h" for sustained traction / LP-yield strategies, "1h" for faster reaction.) To check whether to EXIT, read `momentumSignal` on list_user_lp_positions instead. Use `hookless: true` to exclude pools with a custom hook contract. Use `sortBy` ("apy", "tvl", "volume1d", "volume7d", "signal") with `sortOrder` to control ranking — default is tvl desc. Use `topPerVenue` to limit to top N pools per DEX by APY. Supports filtering by protocol/DEX, tokens, pool type, stablecoin status, and free-text search, with pagination. Required upstream step before zap_into_lp_position. IMPORTANT: The response contains two ID fields — `poolId` (string) must be passed AS-IS to zap_into_lp_position and zap_out_of_lp_position (do NOT construct or modify it), and `id` (number) is used only for analyze_pool.ConnectorNo auth
Matching MCP Servers
- FlicenseAqualityDmaintenanceEnables LLMs to search and retrieve academic papers from arXiv by topic, author, category, or ID.5-
- AlicenseAqualityAmaintenanceMCP server for scientific grounding: search and discover open-access research papers across arXiv, OpenAlex, Crossref, PubMed, and Semantic Scholar, and retrieve references/citations from paywalled journals via public DOI/abstract metadata.3240 PyPI7MIT
Matching MCP Connectors
- Research Papers MCPOAuth
Research papers for AI agents: PubMed, arXiv, Crossref; citations, references, open access texts
Free, read-only psilocybin/psilocin papers, trials, citations and verified research datasets.
- Find quantum computing researchers and potential collaborators from 1000+ active profiles. Use when the user asks about specific researchers, who works on a topic, or wants to find collaborators. NOT for jobs (use searchJobs) or papers (use searchPapers). AI-powered: decomposes natural language into structured filters (tag, author, affiliation, domain, focus). Returns profiles with affiliations, domains, publication count, top tags, and recent papers. Data from arXiv papers published in the last 12 months. Max 50 results. Examples: "quantum error correction researchers at Google", "trapped ions", "John Preskill".ConnectorNo auth
- Use this read-only composite workflow tool for opportunity and alpha screening across the current DeltaSignal issuer universe. It server-enforces the alpha-sweep call plan: readiness, alpha_opportunities with limit 15, and daily_changes; alpha_opportunities defaults to operating-company issuers. Parameters: optional output_mode=compact only; do not pass limit, offset, ticker, source_date, or issuer filters because this preset owns exact arguments internally. Behavior: read-only and idempotent; it performs three internal HTTPS reads, has no destructive side effects, never calls issuer-level tools, and preserves partial results if one internal call fails. Use it when the user asks for alpha opportunities, opportunity sweep, clean alpha board, or names worth follow-up research; treat the result as a screen requiring issuer drilldown.ConnectorNo auth
- Use this read-only composite workflow tool for opportunity and alpha screening across the current DeltaSignal issuer universe. It server-enforces the alpha-sweep call plan: readiness, alpha_opportunities with limit 15, and daily_changes; alpha_opportunities defaults to operating-company issuers. Parameters: optional output_mode=compact only; do not pass limit, offset, ticker, source_date, or issuer filters because this preset owns exact arguments internally. Behavior: read-only and idempotent; it performs three internal HTTPS reads, has no destructive side effects, never calls issuer-level tools, and preserves partial results if one internal call fails. Use it when the user asks for alpha opportunities, opportunity sweep, clean alpha board, or names worth follow-up research; treat the result as a screen requiring issuer drilldown.ConnectorNo auth
- Delete a physical product. Requires confirm set to DELETE. Before offering this action or requesting its inputs, check business permissions. FREE businesses cannot use this tool, regardless of individual feature rows. Call check_business_tool_access before collecting inputs. Show any grace-period warning and verified resubscribe link before continuing, and never proceed when access is blocked.ConnectorDestructiveNo auth
- Use first when a buyer is exploring LeadProof without supplying workflow data. Returns the official no-purchase sequence: buyer guide, fictional example audit, browser-only calculator, public workflow tests, and no-card trial. For a scored workflow diagnosis, use audit_lead_workflow; for replay testing, use get_leadproof_replay_trial; for paid checkout, use get_leadproof_checkout only after authorization.ConnectorNo auth
- Plan the parallel sub-analyses for a threat-modeling phase. Given the current phase of a threat_model workflow (its id comes from get_current_step) and your workflow context, returns the recommended breakdown: which analysis prompts to run, with what arguments, which can run in parallel, and an inline fallback for MCP clients that cannot invoke prompts. phase_id is one of: phase_0b_scope_check, phase_1_scope_and_dfd, phase_2_stride_enumeration, phase_2b_domain_challenge, phase_3_scoring, phase_3b_threat_enrichment, phase_5_mitigation, gap_assess_controls. Optional — the workflow works without it; use it to speed up large systems by fanning phases out to subagents.ConnectorOAuth
- Fetch current trending crypto stories with sentiment analysis ## When to use vs `combined_trends_tool` Prefer this tool when only stories are needed: it is the cheap, fast path and has no per-tool rate-limit sub-cap. `combined_trends_tool` is a superset — same stories plus trending words, their context and AI-generated bull/bear summaries — but it calls an LLM, so it is slower and capped much lower per plan. Use it only when trending *words* or those summaries are actually needed, and never call both for the same question. ## Parameters - `time_period` - Time period for trending stories (e.g., '1h', '6h', '1d', '7d'). Defaults to '1h' (last hour). - `size` - Number of trending stories to return (max 10). Defaults to 10. ## Response - `trending_stories` - List of trending stories. - `time_period` - Time period for trending stories. - `size` - Number of trending stories to return. - `period_start` - Start time of the time period. - `period_end` - End time of the time period. - `total_time_periods` - Total number of time periods. ## Trending stories - `title` - Title of the story. - `summary` - Summary of the story. - `bearish_sentiment_ratio` - Bearish sentiment ratio. - `bullish_sentiment_ratio` - Bullish sentiment ratio. - `score` - Score of the story. - `query` - Query used to find the story. - `related_tokens` - List of related tokens. They have the format `BTC_bitcoin` - first part is the ticker, second part is the slug in Sanbase.ConnectorNo auth
- Report this server's own release version and which Bible data it has loaded, including each edition's licence, required attribution and how many verses it may quote verbatim per call. Use when asked which version runs, when collecting facts for a bug report, and before planning a longer quotation. Returns no scripture — use bible_lookup for verse text.ConnectorNo auth
- Get Alex Polonsky's curated public professional profile, including selected experience, demonstrated capabilities, journalism background, public projects, and future professional directions. This is selected evidence, not a complete CV. When summarizing examples, preserve their ownership qualifier exactly: led, owned_key_aspects, or contributed. Do not infer stronger ownership. If a list mixes things Alex built with work he contributed to or helped bring to market, frame it as built or contributed to, not built. Keep the action verbs and limits from contribution; do not reduce a contribution to an artifact name. Separate demonstrated experience from future directions. Use get_availability for current opportunity status.ConnectorNo auth
- List recent workflow runs, newest first (workflows group). Filter rather than paginate: status, workflowId, batchId, fileNameContains. Workflow batches have no batch-get endpoint — track them here via batchId. NEEDS_REVIEW runs are paused for human review. hasMore: true means more items exist — prefer narrowing filters over paginating, and pass nextPageToken only when every item is needed.ConnectorOAuth
- Permanently delete a form and every response it has collected. This is not the same as closing a form — if someone wants to stop collecting answers but keep them, call set_form_status with "closed" instead. Requires confirm: true. Do not pass it on a vague instruction; ask the person to confirm they want the responses destroyed, and say how many there are.ConnectorDestructiveOAuth
- Search the PUBLIC Awareness knowledge graph — 1,000+ sourced scientific papers. Use this when the user (especially a researcher or a research agent) asks for peer-reviewed findings: "latest evidence on X", "highly-cited papers about Y", "what does the literature say about Z". This is NOT a memory tool — it does not read the user's private memory, and it needs no per-user API key, so it works even when Awareness memory is not configured (the MCP connection itself still needs its own token). Coverage: condensed-matter, quantum-information, materials, machine-learning, renewable-energy, chemistry, biology, medicine, neuroscience, computer-science (2022-2026, cited >= 50), plus a business supply/demand domain. What comes back (anonymous preview mode): title, snippet (preview), confidence, source_ref (DOI), citation_count, domain/topic, and a detail page URL. Full content is NOT in the preview — tell the user it is paid retrieval via POST /api/v1/public/retrieve with an API key (see https://awareness.market/en/knowledge for the KaaS product). Args: query: Natural-language research question or keywords (2-1000 chars). domain: "science" (default) or "business". topic: Optional sub-topic slug, e.g. "medicine", "condensed-matter", "supply-chain". Empty = search all topics in the domain. top_k: Max results, 1-20 (default 5; anonymous callers are capped at 3). include_graph: When true, also return same-topic related items. Returns: {"results": [{id, title, snippet, confidence, source_ref, citation_count, domain, topic, url}], "related": [...], "total": int, "mode": str} `mode` is "preview" (anonymous) or "full" (authenticated).ConnectorNo auth
- Search Lacuna's ML/AI corpus for papers, research directions, authors, venues, institutions, novel research hypotheses, and research resources (code repositories, datasets, models, and demos linked to papers). For novel ML/AI research ideas, use search_type="hypothesis", then get_hypothesis on promising results. search_type accepts all, cluster, paper, author, institution, venue, hypothesis, or resource. Use paper for literature and get_paper to read a result. Use other sources for biographies, news, and non-research web content. Resources: search_type="resource" searches GitHub repositories, Hugging Face datasets/models, and Zenodo records that Lacuna has linked to at least one paper. To find benchmark or evaluation datasets, use search_type="resource" with resource_kind="dataset" (for example query "image classification benchmark" or a dataset name like "ImageNet"). resource_kind accepts codebase, dataset, model, or demo (one value or a list); provider accepts github, huggingface, or zenodo. Both filters require search_type "resource" or "all" (with either filter set, only resources are returned). Each result has an external `url`, a Lacuna `context_url`, and `linked_paper_count`; call get_resource on its id to list the linked papers (with their relationship to the resource), then get_paper on those papers for reported results and numbers. Resource search does not support date_from/date_to, venue, year sorting, or semantic ranking. ranking_profile accepts: - default / lexical (default): production ranking; relevance-sorted paper searches combine lexical and semantic retrieval when fields is unset. - semantic: conceptual paper retrieval; supported for paper and all. - bm25_title_abstract / bm25: lexical paper matching over those fields. sort accepts relevance (default), year_desc, or year_asc. Semantic ranking cannot use year sorting; constrain recency with date_from/date_to instead. date_from and date_to are inclusive YYYY, YYYY-MM, or YYYY-MM-DD bounds. author_id_or_url constrains a paper search to one author. Pass an author ID or Lacuna author page URL; it requires search_type="paper". fields optionally restricts and weights lexical fields, for example "title^4,abstract". Supported names are title, abstract, summary, concepts, name, top_names, and venue, plus description, topics, provider_key, and paper_titles for resources (a resource's title already includes its description, topics, README text, and linked paper titles). Fields must exist on the selected search_type, weights must be within 0 < weight <= 100, and fields cannot be combined with semantic ranking.ConnectorNo auth
- Starts the live (published) version of an API-triggered workflow for 1–100 recipients. It sends real notifications. Read the workflow with workflows_get first (its payload schema names the data fields). Set dry_run to only check the data against the payload schema: nothing is sent. To test a draft, use workflows_test_run; for an event-triggered workflow, use events_track. Right after workflows_publish, it can answer 404 for about a minute: wait and try again.ConnectorDestructiveOAuth
- Runs the draft (default) or the live version of a workflow once, for test recipients, so you can test changes before workflows_publish. It sends real notifications. SuprSend checks the version and the data first; there is no dry run (to check data only, use workflows_trigger with dry_run). API-triggered workflows need recipients; event-triggered workflows need distinct_id (and event, if the workflow listens for more than one). workflows_get shows the trigger type.ConnectorDestructiveOAuth