"Understanding the Purpose of Research" matching MCP tools:

• compare

  XFMS — Xpansion Framework Model Source

  Run a live A/B test between 2–5 user-specified models for a stated purpose. NO ranking step — the supplied model_ids ARE the candidate set. Generates 5 representative test queries from the purpose, runs them through every named model in parallel, and returns real cost, latency, and plain-English commentary on who won what. Unknown IDs are dropped with a note; if fewer than 2 IDs resolve, the call refuses. Use this whenever the user names specific models to compare (e.g. 'A/B test X and Y'). For engine-chosen candidates, use `benchmark` instead. Costs more than `rank` (10+ live LLM calls). Free-tier note: when any candidate ends in ':free', the probe is capped at 3 queries (no adaptive expansion) because free-tier rate limits often push longer probes past the deploy's 5-minute ceiling — evidence will be shallower. The commentary surfaces this when it happens.

  Connector

• country_banking_rules

  banking-intelligence

  Get banking rules and requirements for a country. Returns IBAN requirements, SEPA membership, FATF listing status, national currency, account format specifications, and country-specific payment requirements (mandatory codes like KNP for Kazakhstan, Purpose of Payment for UAE, etc.). Use this to check country-specific STP rules that could cause payment delays, repairs, or rejections (e.g., missing purpose codes, regulatory fields). If a country requires special payment codes, the response includes a payment_requirements block with field descriptions and categories. Use country_payment_codes to look up specific code values. Args: country_code: ISO 3166-1 alpha-2 code (e.g., "DE", "US", "KZ") Examples: country_banking_rules("DE") country_banking_rules("KZ") # includes KNP requirement info country_banking_rules("AE") # includes Purpose of Payment info

  Connector

• competitive_deep_dive_async

  mcp-knowledge

  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_dive when the agent cannot wait >15s for a response. Inputs: same as competitive_deep_dive — company (required), competitors (optional list, max 5), depth (easy/medium/hard, default medium). Async tool — register a webhook via `webhooks_manage(register, url, [job.completed])` to receive callbacks instead of polling. Faster + lighter.

  Connector

• get_session_dossiers

  VaultCrux Memory Core

  Retrieve pre-synthesized per-session memory dossiers (typed: experience | fact | preference; with When/Involving/To-purpose metadata). Use for multi-session or preference-style questions where stitching across conversations is the bottleneck — the dossier already summarises each session's key events. Two modes: mode='search' with a query (BM25-ish ranking over summary+purpose, optional type_filter), or mode='list' returns the tenant's most-recent dossiers chronologically. Tenants without FEATURE_SESSION_DOSSIERS enabled return an empty list (no error).

  Connector

• get_symbol_peer_links_tool

  OneQAZ Trading Intelligence

  Purpose: Symbol-level lead-lag links (e.g. META -> AMZN, lag=15m, rho=+0.53). When `symbol` is set, only peers that lead or follow that symbol are returned. When to call: incorporate peer leading signals into single-symbol reasoning. Prerequisites: none. Next steps: get_signal_detail for the peer's signal context. Caveats: 14-day lookback, 15-minute bars. Args: market_id: coin / kr_stock / us_stock symbol: Optional. When set, peers are anchored to this symbol. top_k: Number of top links to return Disclaimer: Information only, not investment advice.

  Connector

• compare

  XFMS — Model Source

  Run a live A/B test between 2–5 user-specified models for a stated purpose. NO ranking step — the supplied model_ids ARE the candidate set. Generates 5 representative test queries from the purpose, runs them through every named model in parallel, and returns real cost, latency, and plain-English commentary on who won what. Unknown IDs are dropped with a note; if fewer than 2 IDs resolve, the call refuses. Use this whenever the user names specific models to compare (e.g. 'A/B test X and Y'). For engine-chosen candidates, use `benchmark` instead. Costs more than `rank` (10+ live LLM calls). Free-tier note: when any candidate ends in ':free', the probe is capped at 3 queries (no adaptive expansion) because free-tier rate limits often push longer probes past the deploy's 5-minute ceiling — evidence will be shallower. The commentary surfaces this when it happens.

  Connector

• get_sector_correlations_tool

  OneQAZ Trading Intelligence

  Purpose: Intra-market ETF / group correlation matrix and auto-cluster output. Quantifies structural co-movement (e.g. ARKK <-> QQQ) for diversification and sector-avoidance reasoning. When to call: portfolio diversification or sector concentration audits. Prerequisites: none. Next steps: get_symbol_peer_links_tool for per-symbol lead-lag inside a sector. Caveats: refreshed every 6 hours; 60-day lookback. Args: market_id: coin / kr_stock / us_stock top_k: Number of top pairs to return Disclaimer: Information only, not investment advice.

  Connector

• explain_decision

  OneQAZ Trading Intelligence

  Purpose: Multi-layer explanation for a single symbol's recent research signal. Combines (1) technical score_trace from the signals store, (2) Thompson + regime scores from the virtual decision log, (3) news causality context. Use this when an AI must present a structured "why" rather than a raw verdict. When to call: when the user asks "why is this signal bullish/bearish?". Prerequisites: identify the symbol via get_signals or get_latest_decisions first. Next steps: none (this completes the explanation chain). Caveats: `symbol` must match the per-symbol signal store filename (lowercase). Output is research evidence, NOT a buy or sell recommendation. Args: market_id: Market identifier (crypto, kr_stock, us_stock; aliases coin/kr/us) symbol: Symbol to explain (e.g., btc, eth, 005930) Disclaimer: Information only, not investment advice.

  Connector

• get_strategy_leaderboard

  OneQAZ Trading Intelligence

  Purpose: Top RL-learned research strategies — GLOBAL pool + per-symbol partition. Layer E evidence. The GLOBAL pool may include synthesized win_rate values, so per_symbol_leaderboard is the primary measured-edge surface for trust auditing. When to call: final trust-validation step. Prerequisites: none. Next steps: market://{market_id}/signals/summary for live signals. Caveats: `min_trades` filter enforces statistical validity. Strategies are paper-tested, not real-money executed. Args: market_id: Market identifier (crypto, kr_stock, us_stock) target_market: Alias for market_id (backward compat) top_n: Top N strategies to return (default 20) limit: Alias for top_n (client-compat) min_trades: Minimum trades count for inclusion (default 10) include_per_symbol: Include per-symbol PG partition results (default True) Disclaimer: Information only, not investment advice.

  Connector

• get_auth_session

  agentView

  Polls the status of a login session created by create_auth_session. Use this after create_auth_session; poll every 2-3 seconds until the status is no longer 'pending'. Do not use this for any other purpose. Returns one of three states: 'pending' (user has not logged in yet — keep polling), 'active' (login succeeded; tokenExpiresAt is an ISO 8601 timestamp for when re-authentication is required. For security the raw bearer token is intentionally not returned over MCP, so keep using your session_request_id on protected calls), or 'expired' (login window or token timed out — call create_auth_session again). When status is active the current MCP session is automatically authenticated; you can call protected tools immediately.

  Connector

• congressgov_bill_summaries

  congressgov-mcp-server

  Browse recent CRS (Congressional Research Service) bill summaries — plain-language summaries of bills at each legislative stage, useful for answering "what's happening in Congress?". The fromDateTime/toDateTime filters apply to the summary's update time, not the bill's action date, so results include recently rewritten summaries of older bills. Defaults to summaries updated in the last 7 days. Each item shows both the bill's action date and the summary update date. For summaries of one specific bill, use congressgov_bill_lookup with operation='summaries' instead.

  Connector

• gbif_get_species_classification

  gbif-biodiversity-mcp-server

  Return the complete parent chain for a taxon — from kingdom (or domain) down to the taxon itself — as an ordered array. Each entry has its rank, canonical name, and taxon key. The array is returned root-first (kingdom → phylum → class → … → parent of given taxon). Useful for building taxonomic trees or understanding placement without navigating the backbone level-by-level.

  Connector

• defillama-pack

  The Stall

  DeFi research pack: returns TVL, chain breakdown, fees, and native token price for 1–3 protocols in one call. Collapses the defillama-protocol + defillama-coin-price 2-call chain at 70% of combined cost ($0.034→$0.024). Same DefiLlama upstreams, zero auth.

  Connector

• create_api_key

  Molt2Meet

  Generate a new API key for your agent. The full plaintext key (m2m_...) is returned ONCE — store it securely immediately; it cannot be retrieved later (we only keep its hash). Use keyName to identify the key's purpose (e.g. 'production', 'staging'). Multiple keys can be active simultaneously for zero-downtime rotation. Requires: an existing API key from register_agent. Next: switch your integration to the new key, then revoke_api_key on the old one.

  Connector

• competitive_deep_dive_async

  gapup-mcp

  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_dive when the agent cannot wait >15s for a response. Inputs: same as competitive_deep_dive — company (required), competitors (optional list, max 5), depth (easy/medium/hard, default medium). Async tool — register a webhook via `webhooks_manage(register, url, [job.completed])` to receive callbacks instead of polling. Faster + lighter.

  Connector

• research

  Sofya

  Perform comprehensive research on a topic. Decomposes your query into sub-queries, searches and reads multiple sources in parallel, then synthesizes a structured report with citations. Best for open-ended or comparative questions that need coverage from many angles. For simple factual lookups, use search instead (optionally with include_answer=true for cheap synthesis). Costs 25 credits. Returns: query, report (structured markdown with citations), sources (array of {title, url, fetched}), sub_queries (the decomposed queries), credits_used, credits_remaining, usage (token counts). Args: query: The research question or topic topic: "general" (default) or "news" (prioritize recent news articles) freshness: Filter by recency - "day", "week", "month", "year", or "YYYY-MM-DD:YYYY-MM-DD" max_sources: Maximum number of sources to use, 5-30 (default 20)

  Connector

• assess_location_aq

  Hermes — Air Quality Intelligence

  Comprehensive air quality assessment for a location in one call. Combines nearby monitor discovery and current readings with DAQI into a single response. Use this as the first tool call for any air quality question about a location. For long-term trend analysis, use the dedicated `trend_analysis` tool. Returns a structured 'summary' dict with purpose-appropriate sections. Present the summary description to users first. Args: location: Postcode, place name, or "lat,lon". purpose: What the user needs — "general" (default), "health" (safety/worry), "exercise" (outdoor activity), or "planning" (homebuying/school assessment/long-term).

  Connector

• list_pages

  California Justice Watch

  Return the canonical list of pages on cajusticewatch.com — slug, URL, label, and purpose. Use this when the user asks about features/pages/tools of the site, OR when you need to recommend a page, OR before saying "I do not have access to X" — the page may actually exist.

  Connector

• recommend_template

  mdmagic-mcp-server

  Suggest the best built-in template(s) for a described purpose. Use this when the user describes WHAT the document is (e.g. 'Q4 board pack', 'API reference', 'wedding invitation', 'legal contract') without naming a template. Returns ranked recommendations with rationale. Why this exists: AI assistants often guess template names that don't exist. This tool maps purpose → real template names from MDMagic's catalog, so convert_document doesn't fail with 'template not found'.

  Connector

• get_knowledge_stats

  mcp-klever-vm

  Get summary statistics of the Klever VM knowledge base. Returns total entry count, counts broken down by context type (code_example, best_practice, security_tip, etc.), and a sample entry title for each type. Useful for understanding what knowledge is available before querying.

  Connector