"Medium" matching MCP tools:

• list_signals

  mcp

  [RAW FEED — engine inputs, NOT trade calls] List active n0brains signals with optional filters. Filters: asset (e.g. 'ETH'), signal_type (whale|sentiment|listing|regulatory|macro|macro_pulse|liquidation|funding|hack|price|other), direction (bullish|bearish|neutral), urgency (high|medium|low), min_confidence, min_score, limit (1-100, default 20), offset. Each signal includes historical_edge, paired_inverse, signal_latency_secs, priced_in_*, calibration_inverted_in_cell. CONFIDENCE CONTRACT: confidence = calibrated empirical win-probability estimate (binned per signal_type), NOT raw model output; when confidence is null, confidence_suppressed_reason says why; confidence_status is one of calibrated|floor_demoted_at_emit|suppressed_anti_predictive|demoted_anti_predictive_type. Transform emitters (whale_position leaderboard fade) carry observed_direction/observed_behavior/model_transform/predicted_direction so the raw observation is never lost. Most rows carry action_hint=ignore — engine inputs, not calls; read historical_edge (cell win_rate) before echoing any direction. For tradeable output use get_actionable_signals.

  Connector

• smithsonian_browse_category

  smithsonian-mcp-server

  Browse Smithsonian objects within one exact category — a single museum (mode "museum"), culture, indexed date term (mode "period"), object type (mode "medium"), or subject term (mode "topic"). The value must be an exact indexed category term, not free text: resolve museum, culture, period, and topic vocabulary with smithsonian_list_terms first (object_type is not enumerable there — harvest it from smithsonian_search_objects results, and treat each casing as its own category, since a harvested object_type covers only the casing it was written in). Returns the category total count, a page of matching objects, and a museum breakdown of that page; page the full category with start and rows. For open-ended or topic discovery, start with smithsonian_search_objects instead.

  Connector

• met_search_collections

  met-museum-mcp-server

  Search the Metropolitan Museum of Art collection by keyword and optional filters. Returns the total match count and a page of matching object IDs, which met_get_object resolves to full records. Relevance is keyword-based, not semantic; department and geographic filters narrow results more than a longer query. The medium parameter maps to the classification field (pass "Paintings", "Drawings", etc., not material descriptions like "Oil on canvas"). isPublicDomain guarantees CC0-licensed images; hasImages also includes copyrighted works. isOnView restricts results to works currently on display in a Met gallery.

  Connector

• url.qa

  DocImprint

  Fetch a public HTTPS URL and answer a specific question about its content. Lean mode — no bundle stored. Use when you have a precise question about a web page. For a broad summary, use url.summarize. For multi-document Q&A, use collection.ask instead. Returns: { url, answer, answer_cited: { value, confidence, citations[] }, confidence: "high"|"medium"|"low", truncated } Example prompts: - "What is the refund policy at https://docs.example.com/policy?" - "Look at [URL] and tell me what the delivery terms are." - "Answer this question based on the content of [URL]: [question]."

  Connector

• document.check_claims

  api

  Verify a list of factual claims against document text. Uses a quality AI model with citation-level evidence. Use after document.extract_text or url.extract when you need to validate specific factual assertions. For open-ended questions about a document, use url.qa instead. For multi-document investigation, use collection.ask. Typical workflow: document.extract_text/url.extract → document.check_claims. Returns: { claims: [{ claim, status: "supported"|"contradicted"|"not_found", evidence: { quote, paragraphs[] }, confidence: "high"|"medium"|"low" }], truncated: boolean } Example prompts: - "Check whether this contract mentions a liability cap of $1M." - "Verify these claims against the document: [claims list]." - "Does the report actually say revenue grew 23%?"

  Connector

• list_signals

  n0brains

  [RAW FEED — engine inputs, NOT trade calls] List active n0brains signals with optional filters. Filters: asset (e.g. 'ETH'), signal_type (whale|sentiment|listing|regulatory|macro|macro_pulse|liquidation|funding|hack|price|other), direction (bullish|bearish|neutral), urgency (high|medium|low), min_confidence, min_score, limit (1-100, default 20), offset. Each signal includes historical_edge, paired_inverse, signal_latency_secs, priced_in_*, calibration_inverted_in_cell. CONFIDENCE CONTRACT: confidence = calibrated empirical win-probability estimate (binned per signal_type), NOT raw model output; when confidence is null, confidence_suppressed_reason says why; confidence_status is one of calibrated|floor_demoted_at_emit|suppressed_anti_predictive|demoted_anti_predictive_type. Transform emitters (whale_position leaderboard fade) carry observed_direction/observed_behavior/model_transform/predicted_direction so the raw observation is never lost. Most rows carry action_hint=ignore — engine inputs, not calls; read historical_edge (cell win_rate) before echoing any direction. For tradeable output use get_actionable_signals.

  Connector

• GetEconomicCalendar

  equibles

  Get the economic release calendar — scheduled (upcoming) and recent publication dates of US macro data releases, with the FRED series each release updates and an importance tier per release (High = the tier-1 scheduled market movers: CPI, PPI, Employment Situation, GDP, PCE, retail sales; Medium = other genuine scheduled prints; Low = daily rate/market levels like SOFR or VIX). FOMC meetings are NOT included — FRED's release feed has no real FOMC meeting dates; use the Federal Reserve's published meeting calendar for those. Defaults to the next 30 days. Use minImportance=high to see only the market movers, and GetEconomicIndicator to fetch a series' data after it prints.

  Connector

• call_creative_worlds

  Heista

  Heista's creative direction engine — same engine the Creative Director specialist runs internally, exposed over MCP. ONE-SHOT: give a brief, get N finished creative outputs. For back-and-forth refinement, or output shapes the `medium` enum below does not cover, use chat_with_creative_worlds instead. OUTPUT SHAPE switches on the `medium` arg: • omitted → N territory cards (default exploration). Each card sits on different psychology / craft / feel / world axis coordinates so the set spans the creative space rather than orbiting one insight. Card has: name, campaign line, 5-8 sentence pitch, one-sentence strategic bet, resolved axis state names, creative-director rationale. • `tvc` → N TVC scripts (15-90s — hook, arc, resolve, sound design, end line). • `billboard` / `ooh` / `print` → N out-of-home concepts (visual concept + line + placement rationale). • `social` → N social-video concepts (hook + format type + middle beat + payoff, optimised for Reels / TikTok / Shorts). • `activation` / `experiential` → N activation concepts (space design + user journey + peak moment + takeaway artifact). • `audio` → N sonic / radio concepts (sonic scene + voice + audio arc). • `campaign` → N full campaign platforms (insight → big idea → strategy → visual world → production roadmap). The engine can also produce manifesto / copy, naming, packaging, PR stunts, content series, brand positioning, partnerships — these output shapes are NOT in the medium enum, so use chat_with_creative_worlds when the user wants one of those. USE WHEN: user says "give me ideas / options / directions / territories", "what angles work for...", "show me three / five ways to...", "write a TVC for...", "draft billboard concepts for...", "I need fresh thinking on...". DO NOT USE to refine one existing direction (use chat tool), to critique work, for OKRs / internal docs / strategy decks, or anything outside advertising creative direction. INPUTS: brief (the creative problem, free text), count (2-6 concepts), optional brand_id (from list_brands or any create_powersource_* — when provided the engine grounds output in the brand's buyer tensions, voice, and selling points), optional medium (above), optional lens_hint (apply a playbook or signature move as a creative constraint), idempotency_key (safely retryable for 5 minutes). Returns the finished creative output as narrative text PLUS a structured array of resolved axis coordinates for programmatic use. Metered — typically 3-15 credits per call depending on count and brand context size. Charged after success on actual token usage.

  Connector

• create_topup

  AfterLaunch

  Create a credit top-up checkout link for THIS product run (the enrollment your key is bound to), the way to refill the credits that pay for metered growth marketing work when the balance runs out. Pass pack_id: a small, medium or large refill pack. Returns a checkout_url the founder opens to pay; once payment succeeds AfterLaunch adds the credits to this product automatically. Requires the 'act' scope and the Founder plan (on a free trial, use create_checkout first: it mints the upgrade link). The top-up is always bound to your own enrollment, so it can never credit a different account.

  Connector

• competitive_deep_dive

  mcp-knowledge

  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 keyless. Returns agent-shaped JSON: KPIs (funding, employees, revenue, market cap), P0/P1/P2 competitive signals, pricing radar, competitor comparison matrix, Wayback timeline, positioning (sector/industry/icp_hypothesis/moat_signals), quality score. Every field is sourced or marked unavailable — no hallucinated figures. SLA: p50 ~25s, p95 ~30s · score 80+ on listed targets (US/EU/foreign) · score ~40 on private companies (no EDGAR/Yahoo data). Use sync for batch agents (≤30s tolerance). Use `competitive_deep_dive_async` + `competitive_deep_dive_result(job_id)` for conversational agents. Inputs: company name or domain (required), optional competitor list (≤5), optional depth (easy/medium/hard).

  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

• competitive_deep_dive

  gapup-mcp

  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 keyless. Returns agent-shaped JSON: KPIs (funding, employees, revenue, market cap), P0/P1/P2 competitive signals, pricing radar, competitor comparison matrix, Wayback timeline, positioning (sector/industry/icp_hypothesis/moat_signals), quality score. Every field is sourced or marked unavailable — no hallucinated figures. SLA: p50 ~25s, p95 ~30s · score 80+ on listed targets (US/EU/foreign) · score ~40 on private companies (no EDGAR/Yahoo data). Use sync for batch agents (≤30s tolerance). Use `competitive_deep_dive_async` + `competitive_deep_dive_result(job_id)` for conversational agents. Inputs: company name or domain (required), optional competitor list (≤5), optional depth (easy/medium/hard).

  Connector

• document.extract_structured

  api

  Extract typed fields from document text using a caller-defined schema. Uses a quality AI model with retry logic. Use when you need specific data points from a document rather than full text. For invoices with known fields, document.parse_invoice (prebuilt schema) may be simpler. For general summarization, use document.summarize instead. Schema format: { "field_name": "type hint or description" } — e.g. { "contract_date": "ISO date", "party_a": "string", "penalty_usd": "number" }. Returns: { data: { <field>: value }, data_cited: { <field>: { value, confidence: "high"|"medium"|"low", citations: [{ quote, paragraphs[] }] } } } Example prompts: - "Extract the contract date, parties, and penalty amount from this agreement." - "Pull the vendor name, PO number, and total from this document." - "Get me all named fields from this form using my custom schema."

  Connector

• get_regulatory_updates

  Crank Protocol

  Recent regulatory statements affecting Crank's scope (free read, ENG-43ba5e83). Returns SEC / CFTC / FinCEN press releases and rule proposals from a scheduled daily scan, LLM-classified for relevance to Crank: DeFi, crypto perps, tokenized equities, autonomous agent trading, and non-custodial custody. Each update carries the issuing ``agency``, title, url, ``relevance`` (high/medium/low) + score, matched ``topics``, and a one-line factual ``summary``; results are ranked by relevance then recency. window_hours bounds the lookback (default 168 = 7 days, capped at 720 = 30 days); min_relevance filters by floor (high/medium/low); agency optionally narrows to one body (SEC, CFTC, FinCEN). Relevance is a compliance-triage signal, not legal advice. Not financial advice. Workflow: INTELLIGENCE / COMPLIANCE step -- check the current regulatory posture around perps, tokenized equities, or agent trading before acting on a strategy.

  Connector

• detect_stack_from_text

  StackSwap

  Infer a GTM stack from a freeform text blob (a careers page, job posting, public site HTML, RFP, 'What we use' doc, browser DevTools network tab, etc.). Returns ranked tool matches with confidence levels (high/medium/low) and evidence snippets, plus a ready-to-use array for chaining into `scan_stack` or `find_overlaps`. Use when the user says 'I don't know what we use' or pastes a competitor's careers page to scout. Conservative on ambiguous short tokens — multi-mention or canonical-name matches win.

  Connector

• competitive_deep_dive

  gapup-mcp

  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 keyless. Returns agent-shaped JSON: KPIs (funding, employees, revenue, market cap), P0/P1/P2 competitive signals, pricing radar, competitor comparison matrix, Wayback timeline, positioning (sector/industry/icp_hypothesis/moat_signals), quality score. Every field is sourced or marked unavailable — no hallucinated figures. SLA: p50 ~25s, p95 ~30s · score 80+ on listed targets (US/EU/foreign) · score ~40 on private companies (no EDGAR/Yahoo data). Use sync for batch agents (≤30s tolerance). Use `competitive_deep_dive_async` + `competitive_deep_dive_result(job_id)` for conversational agents. Inputs: company name or domain (required), optional competitor list (≤5), optional depth (easy/medium/hard).

  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

• calculate_risk_score

  ContrastAPI

  Composite CVE risk score (0-100) — fuses CVSS, EPSS, KEV, and PoC into a single agent-ready triage signal. Formula: CVSS*0.20 + EPSS*0.35 + KEV*0.30 + PoC*0.15 (each component rescaled to 0-100 before weighting). Multiplicative boosters applied in order: KEV+PoC combo (*1.15), critical-severity-with-high-EPSS (CVSS>=9 AND EPSS>0.7, *1.10), recently published (within last 7 days, *1.05). Final score clamped to [0, 100]. Label bands: CRITICAL>=90, HIGH>=70, MEDIUM>=40, LOW<40. Urgency text encodes patch SLA (immediate when KEV; 24h/72h/30d by label). Use to triage a single CVE without orchestrating cve_lookup + exploit_lookup separately. PoC signal here is the local ExploitDB mirror only — for full multi-source exploit detail (GitHub Advisory + Shodan refs + ExploitDB), call exploit_lookup separately. Methodology adapted from mukul975/cve-mcp-server (Apache-2.0): https://github.com/mukul975/cve-mcp-server. Free: 30/hr, Pro: 500/hr. Returns {cve_id, score (0-100), label (CRITICAL/HIGH/MEDIUM/LOW), urgency, has_public_poc, components (cvss_v3, epss_score, in_kev, has_public_poc, weighted_breakdown), boosters_applied, recommendation, summary, verdict, next_calls}.

  Connector

• verify_recipe

  Guardian Engine

  Verify a candidate recipe against a Guardian master recipe. Uses deterministic graph-based verification to check technique, temperature, timing, cooking medium, and required ingredients. **Verdict**: `verdict` is strictly PASSED or FAILED and is policy-driven — any CRITICAL finding fails the recipe; more than 5 WARNINGs also fail. There is no score in the response (ADR-013): gate on `verdict` and explain failures from `findings`. **Field audience**: `issue` is a machine-readable code for programmatic handling — never show it to end users. Use `title` and `suggested_correction` as the user-facing fields. Returns structured JSON by default (machine-actionable findings and patches); response_format="text" renders a human-readable report. Both formats are transparent (ADR-009 / ADR-018): exact values and ingredient names included.

  Connector

• get_master

  Guardian Engine

  Return the canonical master recipe for a dish (read-only, no LLM). Enables compare-then-verify agentic loops: fetch the master, diff it against the user's recipe, then call verify_recipe — instead of verifying blind. Pure knowledge-base lookup, no LLM in the hot path. Master content is transparent by default (ADR-009 / ADR-010): exact temperatures, timings, and EU FIC 1169/2011 allergen codes are returned verbatim, never obfuscated. No score is included (ADR-013) — this is reference data, not a verdict. Returns ingredients, steps (technique/temperature/timing/medium), and the EU FIC allergens derived from the required ingredients. Unknown dishes return a structured UNKNOWN_DISH error.

  Connector