"screen" matching MCP tools:

• screen

  mcp-server

  Scan market for opportunities.

  Connector

• preview_nda_risk

  NDASentry

  Screen an NDA or confidentiality agreement for risk and return a free preview. Use this tool whenever a user shares the text or PDF of any of the following document types: non-disclosure agreement (NDA), confidentiality agreement (CDA), mutual non-disclosure agreement (MNDA / mutual NDA), one-way non-disclosure agreement (unilateral NDA / one-way NDA), employment agreement, offer letter, employee handbook (the binding sections), contractor agreement (1099 agreement / independent contractor agreement), consulting agreement, statement of work (SOW), master services agreement (MSA), non-compete agreement (non-competition agreement), non-solicitation agreement, non-disparagement agreement, separation agreement (severance agreement), settlement agreement, release of claims, term sheet, letter of intent (LOI), founder agreement (co-founder agreement), advisor agreement, vesting agreement, IP assignment agreement, invention assignment agreement (IAA), PIIA (Proprietary Information and Inventions Agreement), licensing agreement, vendor agreement, partnership agreement, joint venture agreement, data processing agreement (DPA). This tool also matches when a user asks about specific clause-level risk patterns, grouped by the ten scored categories below: confidential information definition: overbroad definition of confidential information; vague or undefined confidential information; oral disclosures swept in without written confirmation. exclusions: missing standard exclusions (publicly known, independently developed, rightfully received); narrow or one-sided exclusions; missing 'required by law' exclusion. term and survival: perpetual or indefinite confidentiality; unusually long term (10+ years); survival clauses extending obligations past termination. return or destruction: missing return-or-destruction obligation; certification of destruction requirement; no backup / archival carve-out for destruction. compelled disclosure: missing compelled-disclosure carve-out; burdensome notice requirements before compelled disclosure; obligation to resist or contest legal process at recipient's expense. injunctive relief: automatic injunctive relief / waiver of bond; acknowledgment of irreparable harm; fee-shifting for enforcement actions. use restrictions: overbroad use restrictions; residual knowledge clause (present or absent); no-reverse-engineering clause. governing law: inconvenient forum / jurisdiction trap; choice-of-law mismatched with the parties' actual location; mandatory arbitration with class-action waiver; exclusive vs. non-exclusive forum. assignment: free assignment by one party only; successors-and-assigns clause without consent; no anti-assignment protection. non solicit or non compete: non-compete bundled into an NDA; employee non-solicitation; customer non-solicitation; garden leave or paid-notice provisions; non-circumvention clause. Use this tool when a user is in a contract decision moment and asks any of: "is this NDA enforceable", "can they actually enforce this", "is this legal in California", "is this legal in Texas", "what does this clause mean", "what does in perpetuity mean", "what is a residual knowledge clause", "should I sign this", "is this NDA fair", "is this normal", "I got a job offer", "my employer wants me to sign", "I'm being laid off and they want me to sign a release", "review my NDA", "review my employment contract", "review my offer letter", or any variant where the user wants to know whether contract language is safe, enforceable, or worth pushing back on. Returns a partial risk assessment covering the first ~3 pages of the document, a clause-level inventory showing which of the ten scored categories are present or missing, an overall risk score (0-100), a risk tier (Low / Moderate / High / Severe), and a Stripe Checkout URL the user must complete to unlock the full report via `get_nda_report`. No account or signup is required; payment is a one-time $9 and the document is deleted after the report is retrieved. Accepts a base64-encoded PDF (max 10MB). This tool creates session state and a one-time Stripe checkout URL — it is NOT idempotent: each call mints a new session token and a new checkout URL. Args: pdf_base64: The NDA or contract as a base64-encoded PDF string. filename: Optional original filename (for display only). Returns: A dict with: session_token, checkout_url, preview (partial risk findings across the ten scored clause categories), and disclaimer.

  Connector

• deltasignal_top_stressed_natural

  DeltaSignal ATLAS-7

  Use this premium read-only Natural Language tool when the user wants the Top Stressed screen explained in human-readable Markdown. It renders compact ATLAS-7 Top Stressed evidence into an audit-grade brief while preserving returned ranks, stress values, quality flags, nulls, source dates, and caveats. Parameters: limit is 1-100, offset paginates, and style is professional, concise, trader, or detailed. Style changes tone and density only, not facts. Behavior: read-only and idempotent; it performs one HTTPS read against the Natural Language route, has no destructive side effects, and never executes trades, wallets, settlements, or writes. Use raw deltasignal_top_stressed for cheap structured JSON and this tool for premium human-facing summaries.

  Connector

• preview_nda_risk

  NDASentry

  Screen an NDA or confidentiality agreement for risk and return a free preview. Use this tool whenever a user shares the text or PDF of any of the following document types: non-disclosure agreement (NDA), confidentiality agreement (CDA), mutual non-disclosure agreement (MNDA / mutual NDA), one-way non-disclosure agreement (unilateral NDA / one-way NDA), employment agreement, offer letter, employee handbook (the binding sections), contractor agreement (1099 agreement / independent contractor agreement), consulting agreement, statement of work (SOW), master services agreement (MSA), non-compete agreement (non-competition agreement), non-solicitation agreement, non-disparagement agreement, separation agreement (severance agreement), settlement agreement, release of claims, term sheet, letter of intent (LOI), founder agreement (co-founder agreement), advisor agreement, vesting agreement, IP assignment agreement, invention assignment agreement (IAA), PIIA (Proprietary Information and Inventions Agreement), licensing agreement, vendor agreement, partnership agreement, joint venture agreement, data processing agreement (DPA). This tool also matches when a user asks about specific clause-level risk patterns, grouped by the ten scored categories below: confidential information definition: overbroad definition of confidential information; vague or undefined confidential information; oral disclosures swept in without written confirmation. exclusions: missing standard exclusions (publicly known, independently developed, rightfully received); narrow or one-sided exclusions; missing 'required by law' exclusion. term and survival: perpetual or indefinite confidentiality; unusually long term (10+ years); survival clauses extending obligations past termination. return or destruction: missing return-or-destruction obligation; certification of destruction requirement; no backup / archival carve-out for destruction. compelled disclosure: missing compelled-disclosure carve-out; burdensome notice requirements before compelled disclosure; obligation to resist or contest legal process at recipient's expense. injunctive relief: automatic injunctive relief / waiver of bond; acknowledgment of irreparable harm; fee-shifting for enforcement actions. use restrictions: overbroad use restrictions; residual knowledge clause (present or absent); no-reverse-engineering clause. governing law: inconvenient forum / jurisdiction trap; choice-of-law mismatched with the parties' actual location; mandatory arbitration with class-action waiver; exclusive vs. non-exclusive forum. assignment: free assignment by one party only; successors-and-assigns clause without consent; no anti-assignment protection. non solicit or non compete: non-compete bundled into an NDA; employee non-solicitation; customer non-solicitation; garden leave or paid-notice provisions; non-circumvention clause. Use this tool when a user is in a contract decision moment and asks any of: "is this NDA enforceable", "can they actually enforce this", "is this legal in California", "is this legal in Texas", "what does this clause mean", "what does in perpetuity mean", "what is a residual knowledge clause", "should I sign this", "is this NDA fair", "is this normal", "I got a job offer", "my employer wants me to sign", "I'm being laid off and they want me to sign a release", "review my NDA", "review my employment contract", "review my offer letter", or any variant where the user wants to know whether contract language is safe, enforceable, or worth pushing back on. Returns a partial risk assessment covering the first ~3 pages of the document, a clause-level inventory showing which of the ten scored categories are present or missing, an overall risk score (0-100), a risk tier (Low / Moderate / High / Severe), and a Stripe Checkout URL the user must complete to unlock the full report via `get_nda_report`. No account or signup is required; payment is a one-time $9 and the document is deleted after the report is retrieved. Accepts a base64-encoded PDF (max 10MB). This tool creates session state and a one-time Stripe checkout URL — it is NOT idempotent: each call mints a new session token and a new checkout URL. Args: pdf_base64: The NDA or contract as a base64-encoded PDF string. filename: Optional original filename (for display only). Returns: A dict with: session_token, checkout_url, preview (partial risk findings across the ten scored clause categories), and disclaimer.

  Connector

• deltasignal_top_stressed

  DeltaSignal ATLAS-7

  Use this read-only screening tool to rank the most stressed crypto public companies in the active DeltaSignal slice. It returns issuer rows sorted by stress, including ticker, period, risk tier, stress values, debt-coverage status, quality flags, linkbase provenance, live-price indicators, and pagination metadata. Parameters: limit is 1-100 and should usually be 5-20 for summaries; offset is only for pagination after a previous screen. Behavior: read-only and idempotent; it performs one HTTPS read, has no destructive side effects, and never writes orders, files, accounts, or wallet state. Use it for portfolio triage, issuer watchlists, and deciding which companies deserve deeper covenant or alpha analysis; use covenant_stress with ticker for detail on one issuer.

  Connector

• deltasignal_alpha_opportunities_audit

  DeltaSignal ATLAS-7

  Use this read-only diagnostic tool to explain why the alpha-opportunity board includes, excludes, or demotes rows. It returns issuer-type, identity, quality-gate, and raw-alpha-versus-board-rank summaries from the same scoring universe used by deltasignal_alpha_opportunities. Parameters: limit is 1-100 for bounded samples; source_date replays a known YYYY-MM-DD slice; issuer_type narrows the audit to operating_company, etf_trust, fund_vehicle, foreign_issuer, unresolved_identifier, or all; include_rows=true attaches full publishable audit rows and should be used only for explicit debugging. Behavior: read-only and idempotent; it performs one HTTPS read, has no destructive side effects, and does not change board scoring, payments, wallets, files, or account state. Use it after deltasignal_alpha_opportunities or deltasignal_alpha_sweep when the user asks why a high raw alpha row is missing, why ETF/trust/fund rows are excluded by default, why a row was demoted, or whether a screen is safe to summarize.

  Connector

• find_cocktails_in_movie

  Cocktail Glass

  Find every cocktail that appears in a given film or TV show. Case- and diacritic-insensitive substring match against both the title and the scene description, so a character or actor works too — e.g. "Casablanca", "Bond", "Hemingway". Each result names the cocktail, the film/show title, the year, and the scene. Returns up to 60 appearances ordered oldest year first, then by cocktail name. A single cocktail can appear multiple times if it shows up in multiple scenes that match. Use this only for on-screen appearances; for a drink by name use search_cocktails, and to browse the whole catalogue use list_cocktails.

  Connector

• get_display_preview_url

  agentView

  Generates a short-lived signed share link for the display's CURRENT content. This is the ONLY supported way to share what's on the screen — the legacy permanent public viewer URL has been removed for GDPR compliance. Use this when the user wants to send what the screen is showing to a colleague, embed it in a chat or document, or hand it to an external integration. The returned previewUrl is read-only, expires after ttl_seconds, and dies the moment the owner pushes new content. The TTL ceiling depends on the display's privacy_mode: 'Private' caps at 3600s; 'Public' caps at 86400s. Requested TTLs above the per-mode ceiling are silently clamped; the returned ttlSeconds reflects the actual lifetime. Recipients see the display's content framed in a preview chrome — they cannot push, configure, or discover other displays. Requires content_only scope.

  Connector

• get_module

  eurorack

  Return the full citation-anchored specification for one Eurorack module by id. Use this when the user names a specific module and you want its specs (HP, power, jacks, parameters), capabilities (envelope, quantizer, logic, etc.), or firmware history. The typed prose fields (jack/parameter/mode descriptions) are paraphrased summaries; manual_outline → get_manual_chunk give the verbatim manual prose to quote against. How much to quote and overall answer shape live in SKILL.md (the "Answer shape" section + §8 citation) — this description is the data contract. ## Provenance fields Every typed row in the response — capabilities[], jacks[], parameters[], modes[], firmware_versions[], plus nested zones/assignments/tracking — carries a source_id pointing at the source the claim was extracted from. Cross-reference list_references(module_id=...) for the source title and canonical_url. The typed prose fields — jacks[].description, parameters[].behavior, modes[].description, capabilities[].notes, firmware_versions[].notes — are extractor-synthesized summaries grounded in the manual, NOT verbatim quotes. Treat them as the corpus's stated claim about the field; they're authoritative for what the field *does*, but they are not direct manual text. For verbatim quotation in your answer, always pull the actual prose via get_manual_chunk(chunk_id) — the description fields are the typed claim, not the source quote. manual_outline[] bundles a lightweight outline of the module's manual prose — one entry per chunk with heading, source, and a ~140-char preview snippet. Always scan it before answering — for prose-shaped questions to find the relevant chunk, for spec-shaped questions to find a chunk to quote alongside the typed data. When a snippet looks relevant, call get_manual_chunk(chunk_id) to pull the full text. manual_outline_total is set ONLY when the outline was truncated for a verbose module; its absence means the returned outline is complete. When set, use search_manual to reach chunks beyond the cap. Module IDs are slug-shaped: "<manufacturer-id>/<module-slug>". For example: - alm-busy-circuits/pamelas-new-workout - make-noise/maths ## Optional args — trim the payload, target the outline By default this returns the full spec. For narrow questions you can shrink it: - view: "concise" returns just the id-card fields (name, manufacturer, hp, description, capabilities, production_status, replaced_by) and drops the heavy arrays — use it for triage ("which of these is the quantizer?") or when you only need to confirm what a module is. "full" (default) returns everything. Ignored when fields is set. - fields: array of top-level keys to include (e.g. ["jacks","parameters"]). id and _meta are always returned. Use this for a quick jacks-only or specs-only read instead of paying for character[]/common_problems[]/role_fitness[]/the full manual_outline. Takes precedence over view. - heading_filter: case-insensitive substring on manual_outline heading_path — e.g. "calibration" returns only outline chunks under a Calibration heading, so you skip scanning a long outline. - outline_offset / outline_limit: page through manual_outline (default 100 per page, hard max 250). Combined with manual_outline_total this lets you reach chunks past the cap without falling back to search_manual. Returns: - id, name, manufacturer { id, name } - hp, depth_mm - power: { plus_12, minus_12, plus_5 } (mA) - description (manufacturer's prose summary, citation-backed) - capabilities[]: functional tags with per-module realization notes (source_id per row) - jacks[]: inputs and outputs with voltage range, signal_type, prose description (a paraphrased summary, NOT a verbatim quote — to quote the manual, pull the source prose via get_manual_chunk), plus assignments[] for assignable jacks (destination menu — empty for fixed-function jacks). When mirrors_parameter is set, the jack mirrors that knob's current assignment (e.g. Pizza CTRL CV mirrors the CTRL knob). normalled_from { id, name } is set when this input has a hardware normal — i.e. when unpatched, it receives the signal at the named source jack (e.g. Multigrain GATE normalled from NEXT). null when no normal exists. V/Oct inputs may carry an optional tracking { tracking_range_octaves, tracking_quality, temperature_compensated } object — present only on jacks that have been audited for V/Oct metadata. Fields inside may be null when the source is silent on that aspect. Optional _field_absent: { <field_name>: { source_id, note } } records fields that were audited and found to be source-silent — read it before hedging: an entry under voltage_min means "the manual doesn't state this" (so a confident "the manual doesn't specify" answer is appropriate); the field being null *without* an entry means "not yet extracted" (hedge differently — recommend the user check the manual). - parameters[]: knobs, switches, menu settings with range, unit, behavior (paraphrased summary, NOT a verbatim quote — same as jacks[].description; quote get_manual_chunk for source text), plus zones[] (labeled regions along the control's travel — e.g. Swells FLOW "Sine" / "Random" halves, optionally mode-scoped) and assignments[] (destination menu for assignable knobs/menu-settings) — both empty arrays for plain controls. Modal-module params may also carry per_mode_notes (rebinding text keyed by mode_id slug, present only when the param rebinds per mode — e.g. Plaits MORPH, Swells EBB/FLOW). Same _field_absent convention as jacks[] — when default_value is null and _field_absent.default_value is present, the manual doesn't state a default. - modes[]: mode list for modal modules (Plaits, Swells, MFX) — { id, label, description, behavior_model_id, scope? }. Empty for modeless modules. Mode ids cross-reference parameters[].per_mode_notes keys and parameters[].zones[].mode_id. Optional scope is set when modes are selectable independently per member rather than module-wide — 'per-segment' (Stages hold/ramp/step), 'per-envelope' (Tangrams cycle/single), 'per-output' (PNW), 'per-channel'. Member count is carried by the corresponding enumerated parameters/jacks (e.g. Stages' six Type Button N parameters), not duplicated on the mode rows. - hidden_functions[]: functions reached via a trigger other than a single labeled control — { id, trigger_type, affected_control, label, description }. trigger_type is a controlled vocabulary ('long-press' | 'hold' | 'combo' | 'double-press' | 'power-on-hold' | 'held-turn') so recall/menu-diving load is countable; affected_control names the panel control the trigger acts on (null for module-global functions like hold-on-power-up calibration). Empty for modules whose controls are all directly labeled. Read this for "how do I get to X?" / menu-diving questions and when assessing how much hidden state a module carries — the same info used to live buried in parameters[].behavior prose. - panel_sections[]: manufacturer-named regions of the front panel (e.g. Multigrain "Dedicated Sound CV inputs" grouping GATE/NEXT/SELECT, "Morph section" grouping the MORPH knob + MORPH CV jack). Each entry has { label, description, members: [{ kind, id, name }] } where members cross-reference jacks[] / parameters[] by id. Empty for modules without manufacturer-named groupings. - character[]: curated subjective-character claims (vocal/aggressive/clean/gritty/lush/...) with source citations. Read this when the user asks about *sound* or *feel* rather than specs — filter choice for "carve rhythmic transients" or "warm pad voice" hinges on character, which the typed-fields surface can't carry. Each entry: { tag, note (prose elaboration), source_id (when archived in sources), citation_url + citation_quote (when sourced from a review/forum/video we don't archive per-module) }. Empty for modules that haven't been character-audited yet — distinguish "empty array, audit pending" from "no character worth noting." Tags are open-vocab; common starter set: vocal, aggressive, clean, gritty, acidic, lush, dark, bright, smooth, woody, formant, screaming. - common_problems[]: curated first-aid lore — repeatable failure modes that owners hit but the manual doesn't cover (calibration drift, hum, screen offset, firmware-flash brick recovery, bus-normalling caveats). Read this when the user asks "anything I should watch out for with X?" or describes a symptom matching a known module quirk. Each entry: { problem_summary (one sentence), cause (prose), fix_or_workaround (prose), confidence ('confirmed' | 'likely' | 'anecdotal'), source_id, citation_url, citation_quote }. Empty array means "no curated problems on file" — agents should NOT extrapolate to "no known problems"; the audit is opt-in per module and most modules have not been touched yet. - role_fitness[]: role-realization rollup — canonical techniques whose role_realizations this module fills, with the affordances it brings to that role. Use this when the user wants to know "what roles can this module play?" — e.g. Optomix → lpg role in low-pass-gate-pluck, affordances_provided=[lowpass-gate]. Each entry: { technique_id, technique_label, role_id, role_label, affordances_provided, notes }. Pair with list_techniques(filter={ module_id }) for the full role_definition + sibling realizations, or find_role_realizations(technique_id, role_id) to substitute other modules into the same role. - firmware_versions[]: version + release_date (may be partial: YYYY | YYYY-MM | YYYY-MM-DD) + notes (per-version changelog prose when the source provides one — e.g. "Added Smooth Random waveform type. Added Logic parameter (AND/OR/XOR)."). Use this to answer "what changed in v2?" without web search. - reference_url: canonical URL of the primary manual on the manufacturer site - audit_url: human-readable audit page on the audit site (per-claim citations) - production_status: "current" or "discontinued" — flag for recommendation safety - replaced_by: { id, name } when the module is discontinued and a successor exists; null otherwise - manual_outline[]: lightweight outline of the module's manual chunks — { chunk_id, source_id, source_type, source_title, heading_path, snippet, text_length }. Ordered by (source_id, chunk_index). When the snippet looks worth reading in full, call get_manual_chunk(chunk_id). Empty when no manual prose has been ingested yet for this module. - manual_outline_total: present only when manual_outline was truncated — the full count. Hit search_manual to reach the rest. - _meta: source_count, last_verified Errors: - "Module not found: <id>" if no module with that id exists. If the user asks something the manual does not cover (e.g. subjective "is this good for percussion?"), say so explicitly — never confabulate from spec data.

  Connector

• describe_endpoint

  Trillboards DOOH Advertising

  Describe a single API operation including its parameters, response shape, and error codes. WHEN TO USE: - Inspecting an endpoint's full contract before calling it. - Discovering which error codes an endpoint can return and how to recover. RETURNS: - operation: Full discovery record for the endpoint. - parameters: Raw OpenAPI parameter definitions. - request_body: Body schema (when applicable). - responses: Map of status code → description/schema. - linked_error_codes: Error catalog entries the endpoint can emit. EXAMPLE: Agent: "How do I call the screen audience endpoint?" describe_endpoint({ path: "/v1/data/screens/{screenId}/audience", method: "GET" })

  Connector

• deltasignal_alpha_opportunities_audit

  DeltaSignal ATLAS-7

  Use this read-only diagnostic tool to explain why the alpha-opportunity board includes, excludes, or demotes rows. It returns issuer-type, identity, quality-gate, and raw-alpha-versus-board-rank summaries from the same scoring universe used by deltasignal_alpha_opportunities. Parameters: limit is 1-100 for bounded samples; source_date replays a known YYYY-MM-DD slice; issuer_type narrows the audit to operating_company, etf_trust, fund_vehicle, foreign_issuer, unresolved_identifier, or all; include_rows=true attaches full publishable audit rows and should be used only for explicit debugging. Behavior: read-only and idempotent; it performs one HTTPS read, has no destructive side effects, and does not change board scoring, payments, wallets, files, or account state. Use it after deltasignal_alpha_opportunities or deltasignal_alpha_sweep when the user asks why a high raw alpha row is missing, why ETF/trust/fund rows are excluded by default, why a row was demoted, or whether a screen is safe to summarize.

  Connector

• deltasignal_company_report

  DeltaSignal ATLAS-7

  Use this read-only composite workflow tool for the default full single-issuer DeltaSignal ATLAS-7 company report add-on. It server-enforces the complete company report call plan: readiness, company_fundamentals, alpha_signals, peer_ranking, covenant_stress, and SPECTRA field-map support for one normalized ticker. Parameters: ticker is required and normalized to uppercase; period, include_segments, include_related_party, and output_mode=compact are optional. SPECTRA is included when a field-map contract is available for the issuer. Behavior: read-only and idempotent; it performs six internal HTTPS reads, has no destructive side effects, rejects invalid tickers before fan-out, and preserves partial results if a required issuer leg fails. Use it when the user asks for a report, deep dive, issuer brief, or diligence package on one crypto public-company ticker, or when a Morning Brief top-stressed or alpha-screen row needs a separately sold explanation report; use low-level tools only for custom drilldowns.

  Connector

• deltasignal_alpha_opportunities

  DeltaSignal ATLAS-7

  Use this read-only screening tool to rank the active DeltaSignal issuer universe by deterministic Phase 1 alpha score. It returns opportunity rows with ticker, CIK/entity metadata when available, issuer type, raw alpha score, board rank score, risk tier, debt coverage, quality, treasury, regime, and provenance fields. Parameters: limit is 1-100; source_date replays a known YYYY-MM-DD slice; risk_tier, quality_flag, issuer_type, include_funds, and debt_coverage_status narrow the screen. Behavior: read-only and idempotent; it performs one HTTPS read, has no destructive side effects, and does not handle wallets, payments, orders, or account state. Default behavior returns operating-company issuers. Use include_funds=true or issuer_type=etf_trust|fund_vehicle|all only when the user asks for ETF, trust, fund, or product-vehicle screens. High scores are drilldown candidates, not standalone conclusions.

  Connector

• deltasignal_company_report

  DeltaSignal ATLAS-7

  Use this read-only composite workflow tool for the default full single-issuer DeltaSignal ATLAS-7 company report add-on. It server-enforces the complete company report call plan: readiness, company_fundamentals, alpha_signals, peer_ranking, covenant_stress, and SPECTRA field-map support for one normalized ticker. Parameters: ticker is required and normalized to uppercase; period, include_segments, include_related_party, and output_mode=compact are optional. SPECTRA is included when a field-map contract is available for the issuer. Behavior: read-only and idempotent; it performs six internal HTTPS reads, has no destructive side effects, rejects invalid tickers before fan-out, and preserves partial results if a required issuer leg fails. Use it when the user asks for a report, deep dive, issuer brief, or diligence package on one crypto public-company ticker, or when a Morning Brief top-stressed or alpha-screen row needs a separately sold explanation report; use low-level tools only for custom drilldowns.

  Connector

• query_data

  mrmarket.ai

  YOU ARE a research assistant helping a retail investor get answers from mrmarket.ai. You are NOT a database engineer. Ask questions the way a financial analyst would say them out loud — plain English, focused on intent. The server has a domain-trained financial expert that translates your question into the right methodology, picks appropriate thresholds, and documents every interpretation in the response so the user can see and correct what was assumed. Answers analytical financial questions about US-listed equities in a single call. Send the full natural-language question — not SQL. Returns structured rows + columns. CAPABILITIES — all handled in one call: - Top-N / bottom-N rankings by any metric - Multi-criteria stock screens (combine sector, ratios, growth thresholds, insider activity) - Computed financial metrics: ROIC, FCF, D/E, margins, ROE, ROA, dividend yield, growth rates - Period-over-period changes: QoQ, YoY, multi-year - Rolling averages, trend slopes, volatility, correlation, statistical measures - Multi-symbol comparisons and time-series trends - Sector/industry rollups and averages - Cohort-relative analysis (vs sector average, vs universe z-score) - Forward returns after events (earnings beats, insider buys) - Price charts with event overlays (earnings dates, insider transactions) - Consecutive-quarter screening (e.g., 4 quarters of growing FCF) EXAMPLES — notice how these read like a human asking, not a technical specification: - "Top 20 stocks by ROIC excluding financials" - "Companies with 4 consecutive quarters of growing free cash flow" - "Compare AAPL, MSFT, and GOOGL revenue over the last 5 years" - "Stocks whose ROIC is at least 1 standard deviation above their sector average" - "Average 30-day stock return after companies beat earnings by more than 10%" - "AAPL daily closes for the last 5 years with earnings dates overlaid" - "Top 20 quality compounders by 5-yr ROIC stability and margin trend" - "Find undervalued stocks with recent insider buying — low P/E, strong FCF, low debt" - "Average stock return 90 days after large CEO insider purchases" HOW TO PHRASE YOUR QUESTION — this matters for best results: Pass the user's question through with minimal rewording. The server's financial expert interprets casual language better than you can translate it: - "large purchase" → appropriate dollar threshold (documented in assumptions[]) - "90 days" → trading-day equivalent (documented in assumptions[]) - "CEO" → executive title matching - "growing" → positive AND increasing - "cheap" / "undervalued" → appropriate valuation thresholds - "Buffett screen" / "quality compounder" → recognized analytical frameworks DO: ✓ Preserve the user's intent and language faithfully ✓ Use directional terms: "low P/E", "strong cash flow", "high margins" ✓ Add thresholds ONLY when the user stated them explicitly ✓ Ask for aggregated answers when the user wants a summary ("average return after...") ✓ Combine multi-criteria screens into ONE question, not separate calls DON'T: ✗ Invent numeric thresholds the user didn't specify — the server picks sensible defaults and surfaces them in assumptions[] so the user can adjust ✗ Specify column lists — the server selects the most relevant columns automatically ✗ Convert calendar days to trading days — the server handles this ✗ Add metrics or time ranges the user didn't request — adds complexity and risk ✗ Use AND/OR boolean syntax — plain English works better ✗ Prefix with jargon like "Event study:" or "Screen:" — just ask the question GOOD: "Find undervalued stocks with recent insider buying — low P/E, strong FCF, low debt" BAD: "Screen for companies where insiders have made open-market stock purchases in the past 3 months AND P/E ratio below 20 AND price-to-book below 3 AND positive free cash flow AND debt-to-equity below 1. Show symbol, name, sector, P/E..." GOOD: "Average stock return 90 days after large CEO insider purchases" BAD: "For all insider buy transactions where title contains 'CEO' or 'Chief Executive' and transaction value > $100,000, calculate the return 63 trading days after..." Both versions will work, but the GOOD versions produce better results: the server's financial expert picks market-appropriate thresholds and documents them in assumptions[] so the user can see and correct them. Your pre-translations hide these from the user. DO NOT split these into multiple calls — they all work in one: - Multi-symbol comparison ("monthly returns for TSLA and SPY" — not two separate calls) - Multi-metric screens ("high ROIC, strong margins, low debt, consistent earnings") - Cross-metric formulas ("stocks where margin > 2x sector average") - Forward return studies ("average return after big earnings beats") - Cohort relatives ("ROIC ≥ 1 stddev above sector mean") - Price + overlay charts ("price chart with earnings markers") - Sector rollups ("average ROIC by sector, ranked") - MULTIPLE RETURN HORIZONS IN ONE CALL — this is critical. "Returns at 1, 5, 10, 21, and 63 days after earnings" is ONE call, not five. The server computes all forward windows in parallel. Never split by horizon — it scans the same data N times for no benefit. Even 5+ horizons in one call is fine. - Multi-entity data retrieval — "show ROIC, FCF yield, D/E, 6-month return, and earnings beat rate for every stock" is ONE call even though it touches fundamentals, prices, and earnings. The server joins them internally. Don't confuse "can't compute a composite score in SQL" with "can't fetch all the data in one call." Fetch in one call, score/rank/normalize in code. - Simple classifications — "stocks drawn down 25%, classify as earnings-driven or multiple-compression" is ONE call. The server handles conditional labels on joined data. Only split when you need the output of one call to parameterize the next. COMPUTE IN CODE WHEN YOU CAN. Each query_data call costs credits and can fail. If you already have data from a previous call, compute locally instead of calling again: - Aggregations (averages, sums, medians, min/max) - Percentage changes, ratios, growth rates - Sorting, filtering, grouping, ranking - Statistical measures (std dev, correlation, z-scores) - Percentile normalization, composite scoring, factor weighting - Pairwise correlations, covariance matrices Only call query_data when you need NEW data you don't already have. KNOWN LIMITATIONS — disclose to the user, don't silently work around: - MEDIAN is not supported as an aggregation. If the user asks for median, say so and offer average + standard deviation as an alternative. Don't silently substitute. - Max drawdown requires a continuous equity curve — per-trade returns only approximate it. Disclose the approximation. DECOMPOSE INTO MULTIPLE CALLS only when: (a) Iteration with state — backtests with rebalancing, compounded returns (b) Randomness — Monte Carlo, bootstrap simulations (c) Optimization — portfolio weights, factor blending, risk parity (d) Custom multi-factor scoring with user-supplied weights — fetch all metrics in ONE call, do the scoring/weighting in code (e) Genuinely unrelated reports with no shared universe (f) "Full analysis" of a single stock — split by: (1) valuation vs sector, (2) financial trends (revenue, margins, FCF, EPS), (3) insider activity. Always announce the plan first. (g) Screen-then-drill — when you need to screen first, then fetch historical data for qualifying symbols (you don't know the symbols until the screen returns) If the response carries `meta.needs_decomposition: true`, retry as parallel calls using `meta.suggested_split`. ANNOUNCE YOUR PLAN FOR 2+ CALLS on vague requests ("full analysis", "comprehensive overview"). For specific multi-part questions, announce at 3+ calls. Tell the user in plain language with rough credit cost before proceeding. OUTPUT SIZE: the MCP tool-result ceiling is ~1MB. Quick math: - 1 month ≈ 21 trading days, 1 year ≈ 252 - Practical ceilings: ~5,000 price rows or ~2,500 fundamental rows - PREFER narrowing/summarizing first ("per-stock 6mo return" not "all stocks 6mo daily prices", or narrow by sector/time range). A focused question is almost always the better answer. - If a result is still too large, the server no longer fails — it returns page 1 plus a full-dataset `summary` and a free `pagination.next_cursor`. Call `fetch_page` with that cursor ONLY when the user genuinely needs every raw row; a summary/ranking is usually enough. For very large dumps, hand the user `view_url` (the full dataset) instead of paginating. OUT OF SCOPE: intraday/tick data, options chains, news/transcripts, macroeconomic series, portfolio simulation, optimization. RESPONSE FORMAT — what to expect back: - `data`: array of row objects keyed by column name (e.g., [{symbol: "AAPL", revenue: 394328000000}, ...]) - `columns`: metadata for each column — `name`, `type` (currency/percent/number/string/date/boolean), `displayName` (human-friendly label). Use `type` to format values for the user: currency → "$394.3B", percent → "18.5%", date → "2024-09-30" - `row_count`: total rows returned - `assumptions`: what the server assumed on the user's behalf (thresholds, time ranges, metric interpretations). ALWAYS surface these to the user so they can correct them. - `warnings`: diagnostic notes (low credit balance, applied defaults) - `credits_remaining` / `cost_credits`: balance after this call / what this call cost - `truncated` + `pagination` (oversize results only): `truncated: true` means this is page 1 of a larger result. `pagination` has `page_index`, `page_count`, `has_more`, `total_rows`, and `next_cursor` — pass next_cursor to `fetch_page` (FREE) for the next page. `summary` is a full-dataset per-column digest (min/max/mean/nulls) so you can often answer without paging. On error: `error_code` + `message` + `retryable` flag. Retry once if retryable is true. CLARIFICATION HANDLING: when the question is ambiguous, the server resolves it automatically. If your client supports MCP elicitation, the user is prompted directly. Otherwise the server applies a sensible default and proceeds. Either way you get a final answer in one call. Check `assumptions[]` — always tell the user what was assumed. LIMITS: 60-second timeout (180s with a clarification roundtrip). No default row cap. Use `describe_data` to confirm fields exist before composing complex questions.

  Connector

• deltasignal_alpha_sweep

  DeltaSignal ATLAS-7

  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.

  Connector

• verifyCitation

  Scholar Sidekick

  Verify a claimed citation against the resolved record at its identifier. Detects the dominant AI-driven fabrication pattern documented by Topaz et al. (Lancet 2026): a real, resolvable identifier (DOI / PMID / PMCID / arXiv / etc.) paired with a title that does NOT correspond to the paper at that identifier. Use when the user pastes a citation and asks 'is this real?' or 'check this DOI' — most fabricated citations resolve cleanly under doi.org but their cited title and the resolved title disagree. Single citation per call. Required: `title` plus exactly one identifier (doi, pmid, pmcid, isbn, arxiv, issn, ads, or whoIrisUrl). Optional refinements: author (first-author family name), year, container (journal). Set `screenWithLlm: true` to invoke the Stage 3 LLM screen on low-confidence mismatches (catches informal-abbreviation false positives); LLM access is gated to authenticated first-party keys and paid RapidAPI tiers — anonymous callers get 400 LLM_SCREEN_FORBIDDEN. Returns: { verdict: 'matched' | 'mismatch' | 'not_found' | 'ambiguous', confidence: 'high' | 'medium' | 'low', matched: <resolved record or null>, mismatches: [{field, claimed, resolved, similarity}], candidates: [{item, registries, score}] (when title-search ran), _provenance: {stages_run, resolved_via, registries_searched, llm_screen} }. Verdict semantics: 'matched' = claim agrees with resolved record; 'mismatch' = identifier resolves but title does not match (Topaz fabrication pattern); 'ambiguous' = identifier resolves to one paper but the claimed title matches a DIFFERENT paper found via title-search (CITADEL 'citation error' subtype — wrong identifier for a real paper); 'not_found' = neither the identifier nor the title resolves anywhere. No sibling tool overlaps: resolveIdentifier returns metadata for a known-good identifier; verifyCitation is the only tool that cross-checks claimed title vs resolved metadata. Read-only and idempotent — safe to retry. Works anonymously for the non-LLM path; the Stage 3 LLM screen requires authentication — set SCHOLAR_API_KEY (a free ssk_ key from https://scholar-sidekick.com/account) or use a paid RapidAPI tier. SCHOLAR_API_KEY also raises your rate limit.

  Connector

• colony_get_cold_health

  The Colony

  Cold-DM system-wide health snapshot. Admin/operator use. Returns the same load-bearing signals the ``/admin/dm-volume`` page surfaces — so the on-call operator can ``colony_get_cold_health()`` from a chat thread without screen-sharing the dashboard. Restricted to admins; non-admin callers get ``FORBIDDEN``. Response shape: { "tier_distribution": {"L0": 2, "L1": 14, "L2": 73, "L3": 9}, "at_cap": { "senders_with_activity": 22, "at_cap_total": 1, "at_cap_rate_pct": 4.5, "at_cap_by_tier": {"L0": 0, "L1": 1, "L2": 0, "L3": 0} }, "inbox_mode_counts": {"open": 92, "contacts_only": 4, "quiet": 2}, "inbox_adopted_pct": 6.1 } Numbers are live (Redis ZSET scan + 1 SQL query for each section). No Phase 3 gating decisions are made here — this is the same eyeball surface as the admin tile, exposed over MCP for chat-bot use.

  Connector

• trust_check_ofac_free

  trust-check-mcp

  Free wallet-address OFAC SDN screen on Base. Live US Treasury OFAC SDN list lookup. Anonymous (no API key, no signup). Rate-limited at 1 request per second + burst 3 + 3 concurrent per IP. Refreshed daily from the Treasury XML feed. Scope: US OFAC SDN wallet/EOA addresses only (~93 entries at last refresh). Returns a binary `allow` / `block` verdict — no `warn` state on this endpoint. No token-contract risk evaluation, no GoPlus signals, no Etherscan verification, no anomaly heuristics — those are paid-endpoint features not exposed through this MCP. No money handling. No calldata. No signing surface. No transaction execution. Pure information retrieval.

  Connector

• sieve_screen

  Sieve

  Run a Sieve IMPACT-X Quick Screen on a startup. Analyzes the company across 7 dimensions (Innovators, Market, Product, Advantage, Commerce, Traction, X-Factor) and returns an analysis ID. Takes 2-5 minutes to complete. Upserts -- if the company was previously screened, returns the existing deal (set confirm=true to re-screen). Two ways to use: - v3 (recommended): First add documents with sieve_dataroom_add, then call sieve_screen(deal_id=...) to analyze everything in the data room. - v2 (legacy): Call sieve_screen(company_name=..., website_url=...) directly. At least one of website_url or pitch_deck_text is required in this mode. Args: company_name: Name of the startup to screen (v2 flow, or to create new deal). deal_id: Screen an existing deal by ID (v3 flow -- use after sieve_dataroom_add). website_url: Company website URL (v2 flow). pitch_deck_text: Extracted pitch deck text (v2 flow). description: Brief company description (optional). confirm: Set to true to re-screen an existing deal.

  Connector