"Hypothesis" matching MCP tools:

• check_device_auth

  hypathesis

  Check if the user has completed browser sign-in for a device auth request. Poll this after calling initiate_device_auth. Returns status 'pending' while waiting, or 'complete' with an api_key when the user has signed in. Use the returned api_key as the authorization parameter in other tools. Args: user_code: The user_code returned by initiate_device_auth. Returns: Pending: {"status": "pending"} Complete: {"status": "complete", "api_key": "hk_..."} Error: {"error": "..."}

  Connector

• get_variable_relationships

  hypathesis

  Retrieve analyzed variable relationships for a completed paper. Only returns results when get_analysis_status reports status='Ready'. Without an API key (anonymous): returns the relationship list with source, target, and direction — but detailed reasoning is available only with an API key. Sign up at https://hypathesis.com to get one. Args: file_id: The file_id returned by the /upload endpoint. authorization: Optional. API key as 'Bearer hk_...' or 'hk_...'. Returns: Authenticated: full details (source, target, directed, reason per relationship; name, measure per variable). Anonymous: gated (source, target, directed per relationship; name per variable; sign_up_url for full access).

  Connector

• ask_the_graph

  sniff-mcp

  THE INSTRUMENT — ask a free-form CROSS-SPECIES genetics question and get FILTERED, HONEST HINTS (never a confident guess). It compiles your question into a typed query plan over the dog<->human edge-graph, runs it deterministically, and scores each answer PATH by its weakest edge — returning ranked hints with an evidence TIER (fact / computational / inferred) + citations, or an honest ABSTAIN with a demand signal when the graph can't answer. BEST FOR model-discovery / translational traversal: 'which dog breeds or genes model human <disease>', 'what is the dog ortholog of <gene>', 'what dog disease is phenotypically like <human disease>'. Answers are HYPOTHESIS-GENERATING, not clinical claims: a `fact` hint = an OMIA-curated model-of; a `computational` hint = a conserved 1:1 dog ortholog (a candidate — never 'dogs get this disease'); `inferred` = shared cross-species phenotype. Returns {plan (what it asked the graph), hints:[{answer, tier, score, path (the cited edges), weakest_edge, provenance}], abstain, demand_signal}. Set narrate=true for a gated one-line prose summary per hint (faithful-or-honest-template; it can never fabricate). Use `ask` instead for owner-facing breed/disease/carrier questions; use THIS for human-disease -> dog-model cross-species queries.

  Connector

• get_analysis_status

  hypathesis

  Check the processing status of an uploaded paper. Poll this tool after uploading a PDF until status is 'Ready' before calling get_variable_relationships. Args: file_id: The file_id returned by the /upload endpoint. authorization: Optional. API key as 'Bearer hk_...' or 'hk_...'. Returns: { "status": "Processing" | "Ready" | "Empty" | "Ineligible" | "Pending", "edges_count": int, "variables_count": int }

  Connector

• initiate_device_auth

  hypathesis

  Start a browser-based sign-in flow to get an API key for full access. Call this when you need detailed analysis results (reasoning, measurements) that require authentication. Returns a verification URL to show to the user. After the user signs in, poll check_device_auth with the returned user_code to get the API key. Returns: { "verification_url": str, "user_code": str, "expires_in": 600, "message": str }

  Connector

• self_inspect

  self-inspect-mcp

  Self-Inspect. Express a thought, or describe the task you are working on, and you always get back ONE metathought: a short abstract question that makes you inspect your own task and assumptions before continuing. Use it whenever you want a self-check: after forming a hypothesis, before committing to an answer, when a long chain feels like it has drifted, when you notice you are agreeing to please, or when you are about to assert something from memory. There is no failure case: it always returns a metathought to question yourself with, selected by a transparent heuristic over an open CSV (no LLM). Keyless and free. DO NOT call for factual lookups or as a substitute for doing the task. Absorb the question and act on it; do not echo it verbatim to the user.

  Connector

• review_artifact

  AIOProductOS MCP

  Agent-as-critic over a DRAFT artifact (a feature spec, experiment plan, or page): checks it against a baseline PM bar — clear problem/hypothesis, a measurable success metric, evidence cited, risks named, a rollout/experiment plan — and returns structured findings (section, severity, a CONCRETE suggested fix, and a verbatim evidence quote) plus a 0-100 score. A write: each call re-runs the review and persists it as a new version (see list_artifact_versions). Resolve target_id first — via pm_meta or list_features for a feature, list_experiments for an experiment, list_pages for a page. One small LLM call; use it before sending a draft for sign-off.

  Connector

• get_macro_influence_map

  OneQAZ Trading Intelligence

  Purpose: Expose OneQAZ's pre-defined causal hypothesis map. Each macro category (bonds, forex, vix, credit, liquidity, inflation, commodities, energy) is mapped to a target market with lag_hours + sensitivity. Highest-transparency tool — the causal reasoning is visible and measurable. Triggers (casual questions too): "how do rates affect crypto?", "금리가 코인에 어떻게 영향 줘?", "what's your causal model?", "예측 논리가 뭐야?", "which macro drives which market?". When to call: when an AI wants to understand WHY we make certain predictions. Prerequisites: none. Next steps: get_backtest_tuning_state for runtime calibration of these hypotheses. Caveats: static hypothesis only; see tuning state for current adjustments. Args: market_id: Optional target market filter (coin_market, kr_market, us_market) Disclaimer: Information only, not investment advice.

  Connector

• keep_thinking

  Zephex

  Structure multi-step debugging and planning across tool calls — not a one-shot think. Tracks hypotheses, observations, plans; detects loops via lastActions; riskLevel high/critical blocks dangerous edits (drop table, prod deploy). Loads projectBrief (stack, key_paths, project_memory recall) on local project. On close, suggestedRemember → call project_memory remember. 4 credits hosted. Hard cap 10 thoughts/session. Call when: stuck after 2+ failed debug attempts, auth/billing/schema change spans 3+ files, flaky test you cannot explain, or you need a plan before editing. Pass lastActions (2–5 recent tool calls), goalAnchor after thought 2, sessionId to resume, area for subsystem. NOT when fix is known, single typo, repeating without new evidence, or session ended (nextThoughtNeeded:false). Read thoughtConfirmed and shouldContinue first. Legacy alias: thinking. Example: keep_thinking({ thought: 'Hypothesis: refresh token not rotated in middleware', thoughtType: 'hypothesis', thoughtNumber: 1, totalThoughts: 5, nextThoughtNeeded: true, confidence: 0.6, goalAnchor: 'Fix auth logout loop', lastActions: ['find_code(query=refreshToken)', 'read_code(target=authMiddleware)'], area: 'auth' }). Read-only.

  Connector

• test_hypothesis

  Ground Truth - First Call Activation

  Run a small verification plan made of concrete live checks and summarize whether a hypothesis is supported. Use this when one conclusion depends on multiple simple checks such as endpoint reachability, npm search counts, or whether a page contains an exact substring. This is a coordination tool, not an open-ended research agent: every test must be explicitly defined in advance, and tests run in order with no branching or early exit. The final verdict is mechanical: all tests passing => SUPPORTED, zero passing => REFUTED, otherwise PARTIALLY SUPPORTED. Use verify_claim when you already have evidence URLs, estimate_market for category sizing, and compare_competitors when you already know exact package names.

  Connector

• varrd_ai

  VARRD — Statistically Validated Trading Edges + AI Research Engine

  Talk to VARRD AI (~$0.25/turn). Describe any trading idea in plain language and the system handles everything — loading decades of market data, charting your pattern, running statistical tests, backtesting with stops, and generating exact trade setups. MULTI-TURN: First call creates a session. Keep calling with the same session_id, following context.next_actions each time. 1. Your idea -> VARRD charts pattern 2. 'test it' -> statistical test (event study or backtest) 3. 'show me the trade setup' -> exact entry/stop/target prices HYPOTHESIS INTEGRITY (critical): VARRD tests ONE hypothesis at a time — one formula, one setup. Never combine multiple setups into one formula or ask to 'test all' — each idea must be tested as a separate hypothesis for the statistics to be valid. Say 'start a new hypothesis' between ideas to reset cleanly. - ALLOWED: Test the SAME setup across multiple markets ('test this on ES, NQ, and CL') — same formula, different data. - NOT ALLOWED: Test multiple DIFFERENT formulas/setups at once — each is a separate hypothesis requiring its own chart-test-result cycle. If ELROND council returns 4 setups, test each one separately: chart setup 1 -> test -> results -> 'start new hypothesis' -> chart setup 2 -> etc. KEY CAPABILITIES you can ask for: - 'Use the ELROND council on [market]' -> 8 expert investigators - 'Optimize the stop loss and take profit' -> SL/TP grid search - 'Test this on ES, NQ, and CL' -> multi-market testing - 'Simulate trading this with 1.5 ATR stop' -> backtest with stops EDGE VERDICTS in context.edge_verdict after testing: - STRONG EDGE: Significant vs zero AND vs market baseline - MARGINAL: Significant vs zero only (beats nothing, but real signal) - PINNED: Significant vs market only (flat returns but different from market) - NO EDGE: Neither significant test passed TERMINAL STATES: Stop when context.has_edge is true (edge found) or false (no edge — valid result). Always read context.next_actions.

  Connector

• autonomous_varrd_ai

  VARRD — Statistically Validated Trading Edges + AI Research Engine

  Point VARRD's autonomous AI in a direction and let it discover edges for you. Give it a topic and it draws from one of the most comprehensive market structure knowledge graphs ever built — containing ideologies and theories, not statistics — so it generates genuinely novel hypotheses rather than overfitting to what already worked. BEST FOR: Exploring a space broadly. Give it 'momentum on grains' and it might test wheat seasonal patterns, corn spread reversals, or soybean crush ratio momentum. It propagates from your seed idea into related concepts you might not think of. Returns a complete result — edge or no edge, stats, trade setup. Each call tests ONE hypothesis through the full pipeline (~$0.25/idea). Call again for another idea. Use 'varrd_ai' instead when YOU have a specific idea to test and want full control over each step.

  Connector

• assay_register

  mcp

  Use this when you want to seal a strategy and its success criteria NOW, before the forward data exists, so that registration cannot be adapted or backfilled against those later bars -- a commitment audit, not buy/sell advice. Pre-register a signal NOW; freeze its terms before the forward evidence exists. Signal commitment: your strategy spec (executable JSON DSL) is canonically hashed and committed in tenant state now, then queued for later daily operator-published Merkle inclusion. The register response is not an inclusion proof, and the built-in chain is not independent time evidence; that requires a separately present and pinned external anchor. The later verdict (assay_verdict) uses exclusively data from AFTER registration. That prevents adapting this registration to those forward bars, but does not prove the strategy or family was not selected through earlier research or repeated trials; the family ledger and deflation disclose and penalise those trials. v2: optionally seal a machine-writable HYPOTHESIS tuple alongside the spec -- declared_pass_sharpe_annualized (your pre-committed success bar), max_evaluation_bars (ex-ante window cap: waiting longer than promised cannot improve the verdict), fee_bps_per_side and trading_calendar (the sealed evaluation terms), plus an optional rationale. The tuple is canonically hashed and bound into the same queued commitment as the spec, and assay_verdict ENFORCES it: deviating terms are recomputed under the seal and flagged goalpost_moved -- success criteria chosen after seeing the data are not criteria. Registrations are idempotent, withdrawals still count toward your family's trial budget (anti-gaming). Registrations are keyed to your authenticated account. Price: per check; see https://api.alphaassay.com/v1/meta/pricing (api_key with the register scope required -- account setup at https://api.alphaassay.com/account).

  Connector

• assay_verdict

  mcp

  Use this when a signal was pre-registered with assay_register and the maturity window has passed -- get the post-cutoff verdict computed only from data after registration. A sealed audit, it gives no buy/sell advice. Post-cutoff verdict under the registration's sealed terms. Evaluates a registration strictly on bars AFTER the registration cutoff, with maturity floor and fail-closed data-gap handling (use trading_calendar='weekdays' for equity daily bars so weekends do not count as gaps; omit fee/calendar to use the registration's sealed terms). The verdict embeds the family-deflated Sharpe: even an anchored signal is deflated by how much its family was searched. For v2 registrations with a sealed hypothesis, the verdict additionally reports oos_sharpe_annualized against the pre-committed bar (threshold_met -- a descriptive fact, never an endorsement) and flags goalpost_moved when the requested terms deviate from the sealed ones (the seal always wins). Price: per check; see https://api.alphaassay.com/v1/meta/pricing (api_key required -- account setup at https://api.alphaassay.com/account).

  Connector

• list_experiments

  AIOProductOS MCP

  List product experiments. Returns an array where each experiment carries its hypothesis, the metric it moves, the target, its current state, and — once concluded — the verdict and the decision that came out. Read-only; empty when none match. Use it to see what's being tested before proposing new work, and cite a concluded verdict as evidence when you create_task or review_artifact. Optional product_id (from whoami) and state filter.

  Connector

• p_value

  calc.engineer

  Calculate the p-value for a z-score or t-statistic. Supports one-tailed (left or right) and two-tailed hypothesis tests using either the standard normal distribution or the Student's t-distribution when degrees of freedom are specified. Returns significance flags at the 0.01, 0.05, and 0.10 alpha levels. Essential for interpreting results from t-tests, z-tests, ANOVA post-hoc comparisons, and regression coefficients. Uses the Abramowitz & Stegun normal CDF approximation and regularized incomplete beta function for the t-distribution.

  Connector

• pictify_update_experiment

  mcp

  Update an existing experiment. Available fields depend on the current status: - draft/paused: All fields can be updated (name, slug, variants, goalConfig, banditConfig, hypothesis, etc.) - running: Only name, confidenceThreshold, minimumRunDays, goalConfig.destinationUrl - completed: Only name If updating variants, weights must still sum to 10000.

  Connector

• x711_substrate_seed_hypothesis

  x711

  Inject your hypothesis into the SUBSTRATE evolution engine. Your idea gets a name, an ID, starts at 0.5 fitness, and evolves every 15 min. Can reach breakthrough status — published in the Echo Pack at substratelayer.com. $0.25. Requires API key.

  Connector

• arena_run_grid_backtest

  backtesting-arena

  Simulate a GRID BOT (buy-low / sell-high ladder inside a fixed price range) on historical candles. Returns final value, return %, CAGR, trade count, fees paid and a Buy & Hold comparison. This is a different machine from the strategy backtester: grid bots earn from oscillation inside a range, not from trend — for signal-based strategies use arena_run_backtest instead. The result depends heavily on the range you choose (low_price / high_price); a range the price left early makes the bot idle, so treat range choice as part of the hypothesis, not a detail. Free tier limited to BTCUSDT/ETHUSDT. Per-day quota: Free=5, Pro=50, Power=500. [Free / Pro / Power tier]

  Connector

• synthesize_lead_hypothesis

  freedom-mcp

  Given a lead journey (from query_lead_journey), produce a structured hypothesis: intent score, conversion-failure mode, suggested outreach angle, and notes for drafting. Writes the synthesis back to leads.synopsis_jsonb so the Leads tab UI sees it. Use this after journey reconstruction, before draft_outreach. [write-tier — first use may require a manager's approval; a from-now-on approval makes future calls seamless, a just-once approval re-asks next time.]

  Connector