"Square" matching MCP tools:

• square-root-calculator

  Microapp

  Compute square root, cube root, square, and cube of a number. Returns all four so callers don't have to call four tools.

  Connector

• generate_image

  NotFair-MetaAds

  Generate one image from a prompt using OpenAI GPT Image 2. Returns a public URL you can embed in markdown or pass to a creative-asset tool (e.g. Google Ads `createImageAsset`). Counts against the user's monthly quota. Prompt craft (GPT Image 2 rewards long, specific, instruction-style prompts — write a paragraph, not keywords): - Lead with the medium: photograph, 3D render, isometric vector, watercolor, flat illustration, studio product shot. Single biggest quality lever. - Then specify subject, setting, mood, color palette, lighting (e.g. 'golden hour, soft backlight'), and camera/perspective (close-up, wide, overhead, low angle, macro). - Keep the focal subject in the center 80% of the frame — ad platforms crop edges across placements. - Prefer lifestyle / in-context scenes over isolated-on-white product shots. Google explicitly recommends 'physical settings with organic shadows and lighting' for ad creative. - Don't render text unless the user asks for specific copy. Overlaid text is often unreadable at small ad sizes and Google flags it as a quality issue. - Avoid negative prompts ('no X, no Y'). GPT Image often pulls the rejected concept in — describe what you want instead. Ad-policy rules to bake into prompts: - No collages, borders, watermarks, mirrored / skewed / over-filtered looks. - No fake UI elements (play buttons, download/close icons) — Google Ads policy violation. - Don't overlay a logo on the photo; logos belong inside the scene (on a product, sign, storefront). - Blank space should be under 80% of the frame — the subject is the focus. Aspect ratios — match the target placement: - Google Ads asset slots: '1.91:1' landscape (required), '1:1' square (required), '4:5' portrait, '9:16' vertical (Demand Gen / Shorts). - Meta / social: '1:1' or '4:5' feed; '9:16' stories/reels; '1.91:1' link previews. - Hero / web banners: '16:9' or '3:2'. Default is '1:1'. Quality vs latency: 'low' ~5s drafts; 'medium' balanced; 'high' runs the four-stage Understand/Plan/Generate/Review pipeline (30–50× slower than low) — use only for production-final fidelity. Output format: default 'png' (lossless). Use 'webp' or 'jpeg' for smaller photographic assets. background='transparent' requires png/webp (use for logos, cutouts, UI assets).

  Connector

• asterwise_get_western_natal

  Asterwise

  Calculate a complete Western natal chart using the tropical zodiac and Swiss Ephemeris. Returns 10 planet positions with Placidus (or chosen) house placements, essential dignities, all active aspects, and element/modality/hemisphere balance statistics. SECTION: WHAT THIS TOOL COVERS Tropical natal chart: Sun, Moon, Mercury, Venus, Mars, Jupiter, Saturn, Uranus, Neptune, Pluto. Each planet returns tropical longitude, sign, house (1–12), retrograde flag, dignity label (domicile/exaltation/detriment/fall/peregrine), dignity score (domicile +5, exaltation +4, triplicity +3, term +2, face +1, detriment -5, fall -4), is_exaltation_degree (within 1° of exact exaltation), dignity_disputed (true for outer planets where exaltation/fall is disputed among modern astrologers). Aspect orbs: conjunction/opposition 5°, square/trine 5°, sextile 3°, minor aspects 1.5°. Not Vedic sidereal (asterwise_get_natal_chart). SECTION: WORKFLOW BEFORE: None — this tool is standalone. AFTER: asterwise_get_western_transits_daily — layer current transits over this natal chart. AFTER: asterwise_get_western_synastry — compare this chart against a partner's chart. AFTER: asterwise_get_western_solar_return — annual return chart for the current year. SECTION: INPUT CONTRACT birth.date — YYYY-MM-DD. Example: '1985-11-12' birth.time — HH:MM (24-hour local time). Example: '06:45' birth.lat — Decimal degrees, north positive. Example: 19.076 (Mumbai) birth.lon — Decimal degrees, east positive. Example: 72.8777 (Mumbai) birth.timezone — IANA timezone string. Example: 'Asia/Kolkata', 'America/New_York', 'Europe/Rome', 'UTC'. Default: UTC. IMPORTANT: Timezone defaults to UTC — always supply the correct local timezone for accurate house cusps. An incorrect timezone shifts the Ascendant. birth.house_system — 'placidus' (default, most common), 'koch', 'equal', 'whole_sign'. Placidus is standard for most Western traditions. Whole sign is traditional/Hellenistic. NOTE: house_system is accepted here but silently ignored by transit, return, synastry, composite, and progression endpoints — those always use the birth location coordinates without house-system selection. ayanamsa — always tropical regardless of any value supplied; field is not present. SECTION: OUTPUT CONTRACT data.zodiac (string — 'tropical') data.house_system (string — the system used) data.ascendant — { longitude (float), sign (string), sign_index (int 0–11), degree_in_sign (float) } data.mc — same shape as ascendant data.planets[] — 10 objects (Sun through Pluto): name (string), longitude (float), sign (string), sign_index (int 0–11) degree_in_sign (float), house (int 1–12) is_retrograde (bool), dignity (string), dignity_score (int) is_exaltation_degree (bool), dignity_disputed (bool) data.houses[] — 12 objects: house (int 1–12), cusp_longitude (float), sign (string) sign_index (int 0–11), degree_in_sign (float) data.aspects[] — each: planet_a (string), planet_b (string), type (string) exact_angle (float), orb (float), is_applying (bool) data.elements — { fire (int), earth (int), air (int), water (int), dominant (string) } data.modalities — { cardinal (int), fixed (int), mutable (int), dominant (string) } data.hemisphere — { eastern (int), western (int), northern (int), southern (int) } data.ayanamsa_value (float — 0.0 for tropical) data.ayanamsa_used (string — 'tropical') data.birth_time_provided (bool) SECTION: RESPONSE FORMAT response_format=json serialises the complete response as indented JSON — use this for programmatic parsing, typed clients, and downstream tool chaining. response_format=markdown renders the same data as a human-readable natal report. Both modes return identical underlying data. SECTION: COMPUTE CLASS MEDIUM_COMPUTE (~300ms) SECTION: ERROR CONTRACT INVALID_PARAMS (local — caught before upstream call): — WesternBirthData Pydantic violations (date pattern, time pattern, lat/lon bounds) → MCP INVALID_PARAMS INVALID_PARAMS (upstream): — None expected for valid coordinates and dates post-1800. INTERNAL_ERROR: — Any upstream API failure or timeout → MCP INTERNAL_ERROR Edge cases: — Polar latitudes (above ~65°N or below ~65°S) may cause Placidus house calculation failure; use whole_sign or equal house system for polar births. — time='00:00' accepted; lagna-sensitive results are unreliable for unknown birth times. SECTION: DO NOT CONFUSE WITH asterwise_get_natal_chart — Vedic sidereal chart using Lahiri ayanamsa; different zodiac, different house system, different planet set (9 grahas vs 10 tropical planets). asterwise_get_western_aspects — takes raw longitudes as input; use when you already have positions and don't need full chart computation.

  Connector

• extract_vertical_clip

  Weftly

  Cut a 9:16 vertical clip from any prior video job (find_clips, summarize, or video transcribe), suitable for direct upload to TikTok, Instagram Reels, or YouTube Shorts. Default output is 1080×1920 H.264 / AAC `.mp4` with center-cropped framing; audio loudness-normalized to -14 LUFS / -1.5 dBTP for short-form social. Single-segment only; clip duration must be between 1 and 90 seconds (Instagram Reels max). Operates on a parent job — possessing the parent `source_job_id` is the capability, no upload step. Two-call flow: (1) call with `source_job_id` + `start` + `end` (in source seconds) to receive {job_id, payment_challenge}; (2) pay via MPP and call with `job_id` + `payment_credential` to start processing. Poll get_job_status(job_id) for completion; output is role `clip-vertical-video` (the `.mp4`). Flat price: $0.50 per clip. Payment: pay by credit card via the Stripe Checkout link (open the returned `payment_url` in any browser) or Tempo USDC via mppx. Optional `profile` parameter selects the encoding profile (default `tiktok-primary`). Allowed values: `tiktok-primary` (1080×1920, fast preset, CRF 22), `tiktok-primary-720p` (720×1280, CBR 3 Mbps — half-resolution mobile-optimized, ~40% faster wall time), `instagram-reels` (1080×1920, slow preset, CBR 4 Mbps), `instagram-stories` (same encode shape as instagram-reels). All four profiles loudness-normalize identically. Optional `subject` parameter controls reframing (default `center`, preserves today's behavior): `auto` locks onto the longest-tracked face from the parent's subjects-sidecar (or runs inline detection if the parent has none); `subject_id` (with `subject_id` param naming a face_N from the sidecar) locks onto a specific subject; `follow` switches crop between active speakers across the clip using the sidecar's active_speaker_timeline; `manual` accepts caller-supplied framing via `subject_box: {x, y, w, h}` (source pixels) or `subject_x_offset` (direct crop x). Sidecar shape at /.well-known/weftly-subjects-v1.schema.json. auto/subject_id/follow fall back to center if detection or sidecar resolution fails — the paid job always delivers a clip. Source must be a horizontal video (wider than 9:16) — already-vertical or square sources are rejected. Source must still be in storage (72h TTL for find_clips parents, 24h elsewhere — check `expires_at` from get_job_status on the parent). Pair with `find_clips` ($2.00/video) to pick a moment first, then call this to get a download-ready vertical mp4 in under 5 minutes. Multiple extract_vertical_clip calls against one parent are independent paid jobs. Failed jobs auto-refund.

  Connector

• extract_contract_from_url

  transaction-coordinator

  Extract structured transaction data from a contract at a URL. Downloads the document, extracts text (with OCR fallback for scanned PDFs), and runs PrimaCoda's contract-extraction prompt to return parties, addresses, dates, prices, and key contract fields. Use this when an agent has the contract hosted somewhere (Dropbox, Google Drive direct download, Square Space, etc.) and wants to skip the upload step. For multi-document deals (purchase + addenda + disclosures), use the PrimaCoda dashboard's batch upload — this tool handles ONE document. Args: pdf_url: Direct download URL for the contract (PDF, DOCX, TXT, or image). Must be reachable from the PrimaCoda server. Google Drive "shared link" URLs work if set to "anyone with link"; other share URLs may need their direct-download form. api_key: Your PrimaCoda MCP API key (starts 'pck_').

  Connector

• emem_grid_info

  emem — Earth memory protocol

  Active grid encoding: cell64 ground resolution, lat/lng axis sizes, DGGS lineage. When to use: Call once at session start (or when the user asks about cell resolution / 'how big is a cell'). Returns the actual ground resolution today (~9.54 m × 9.55 m square at the equator (lat 21 bits × lng 22 bits, matching Sentinel-1/Sentinel-2 native pixel pitch). The cell64 bit layout reserves a resolution-tag field for future hierarchical refinement targeting H3-equivalent res-13 (~3.4 m) cells in v0.1.) and the spec target. Useful before you reason about whether one cell is enough or whether you need `emem_recall_polygon`.

  Connector

• generate_image

  NotFair-GoogleAds

  Generate one image from a prompt using OpenAI GPT Image 2. Returns a public URL you can embed in markdown or pass to a creative-asset tool (e.g. Google Ads `createImageAsset`). Counts against the user's monthly quota. Prompt craft (GPT Image 2 rewards long, specific, instruction-style prompts — write a paragraph, not keywords): - Lead with the medium: photograph, 3D render, isometric vector, watercolor, flat illustration, studio product shot. Single biggest quality lever. - Then specify subject, setting, mood, color palette, lighting (e.g. 'golden hour, soft backlight'), and camera/perspective (close-up, wide, overhead, low angle, macro). - Keep the focal subject in the center 80% of the frame — ad platforms crop edges across placements. - Prefer lifestyle / in-context scenes over isolated-on-white product shots. Google explicitly recommends 'physical settings with organic shadows and lighting' for ad creative. - Don't render text unless the user asks for specific copy. Overlaid text is often unreadable at small ad sizes and Google flags it as a quality issue. - Avoid negative prompts ('no X, no Y'). GPT Image often pulls the rejected concept in — describe what you want instead. Ad-policy rules to bake into prompts: - No collages, borders, watermarks, mirrored / skewed / over-filtered looks. - No fake UI elements (play buttons, download/close icons) — Google Ads policy violation. - Don't overlay a logo on the photo; logos belong inside the scene (on a product, sign, storefront). - Blank space should be under 80% of the frame — the subject is the focus. Aspect ratios — match the target placement: - Google Ads asset slots: '1.91:1' landscape (required), '1:1' square (required), '4:5' portrait, '9:16' vertical (Demand Gen / Shorts). - Meta / social: '1:1' or '4:5' feed; '9:16' stories/reels; '1.91:1' link previews. - Hero / web banners: '16:9' or '3:2'. Default is '1:1'. Quality vs latency: 'low' ~5s drafts; 'medium' balanced; 'high' runs the four-stage Understand/Plan/Generate/Review pipeline (30–50× slower than low) — use only for production-final fidelity. Output format: default 'png' (lossless). Use 'webp' or 'jpeg' for smaller photographic assets. background='transparent' requires png/webp (use for logos, cutouts, UI assets).

  Connector

• asterwise_get_lo_shu_grid

  Asterwise

  Derives a Lo Shu three-by-three frequency grid from birth-date digits and annotates planes, missing or repeated digits, and per-digit traits. SECTION: WHAT THIS TOOL COVERS Chinese Lo Shu analysis: counts how often each digit one through nine appears in the date string, lays counts into the classical magic-square positions, and adds plane_analysis plus number_analysis entries keyed by digit strings '1'..'9'. Zero digits are ignored for placement. It does not compute Pythagorean Life Path (asterwise_get_numerology_profile) or Chaldean compounds. SECTION: WORKFLOW BEFORE: None — standalone. AFTER: None. SECTION: INPUT CONTRACT date string only; validated upstream. SECTION: OUTPUT CONTRACT data.birth_date (string) data.grid — three-by-three nested int array (row-major): row positions map to numbers [4,9,2], [3,5,7], [8,1,6] respectively; cell value = count of that digit in the date (0 if absent) data.present_numbers[] (int array) data.missing_numbers[] (int array) data.repeated_numbers[] (int array — digits appearing at least twice) data.plane_analysis: thought_plane — { numbers[] (int array), description (string), complete (bool) } will_plane — same shape action_plane — same shape golden_yod — same shape silver_yod — same shape data.number_analysis{} — keys '1' through '9' (string keys): count (int) plane (string) trait (string) status (string — 'missing', 'present', or 'strong') note (string) SECTION: RESPONSE FORMAT response_format=json serialises the complete response as indented JSON — use this for programmatic parsing, typed clients, and downstream tool chaining. response_format=markdown renders the same data as a human-readable report. Both modes return identical underlying data — no fields are added, removed, or filtered by either mode. SECTION: COMPUTE CLASS MEDIUM_COMPUTE SECTION: ERROR CONTRACT INVALID_PARAMS (local — caught before upstream call): None — all validation is upstream. INVALID_PARAMS (upstream): — None — upstream rejection surfaces as MCP INTERNAL_ERROR at the tool layer. INTERNAL_ERROR: — Any upstream API failure or timeout → MCP INTERNAL_ERROR Edge cases: — Zeros in ISO dates are skipped — only digits one through nine populate the grid. SECTION: DO NOT CONFUSE WITH asterwise_get_numerology_profile — letter-based Western numbers, not digit-frequency Lo Shu. asterwise_get_name_correction — spelling harmonics, not birth-date grids.

  Connector

• asterwise_get_western_aspects

  Asterwise

  Calculates all active aspects between a supplied set of planetary longitudes. Accepts a dictionary of body name to tropical ecliptic longitude and returns every aspect within standard natal orbs. SECTION: WHAT THIS TOOL COVERS Flexible aspect calculator that works with any set of positions — natal planets, transit planets, progressed planets, or custom hypothetical points. Aspect orbs: conjunction/opposition 5°, square/trine 5°, sextile 3°, semisextile/quincunx/semisquare/sesquiquadrate 1.5°. Returns is_applying based on relative speeds if speeds are provided, otherwise assumed separating. SECTION: WORKFLOW BEFORE: None — standalone; or use asterwise_get_western_natal to get positions first. AFTER: None. SECTION: INPUT CONTRACT positions — dict mapping planet/body name (string) to tropical longitude (float 0–360). Must contain at least 2 entries. Example: {'Sun': 229.6, 'Moon': 221.8, 'Mars': 189.6, 'Jupiter': 309.6} Names can be any string — the tool does not enforce planet names. SECTION: OUTPUT CONTRACT data.aspects[] — each: planet_a (string), planet_b (string), type (string — aspect name) exact_angle (float), orb (float), is_applying (bool) data.orbs_used — dict of aspect type to orb value used data.body_count (int — number of input bodies) data.aspect_count (int — number of aspects found) SECTION: RESPONSE FORMAT response_format=json — aspect grid object. response_format=markdown — formatted aspect table. SECTION: COMPUTE CLASS FAST_LOOKUP SECTION: ERROR CONTRACT INVALID_PARAMS (local): — fewer than 2 bodies in positions dict → MCP INVALID_PARAMS immediately. INTERNAL_ERROR: Any upstream API failure → MCP INTERNAL_ERROR SECTION: DO NOT CONFUSE WITH asterwise_get_western_natal — computes both positions and aspects from birth data. asterwise_get_western_synastry — inter-chart aspects between two people.

  Connector

• import_booking_url

  Agent Broker

  Turn ANY public booking URL (Cal.com, Calendly, Doctolib, Booksy, Fresha, OpenTable, Setmore, Square, Acuity, Schedulista, Squarespace, BookMyCity) into a callable smb_id you can immediately use with schedule_appointment, send_message, or capture_lead. Idempotent — calling twice returns the same smb_id. EXAMPLE USER QUERIES THAT MATCH THIS TOOL: user: "Book me a haircut at https://cal.com/jane-salon" -> call import_booking_url({"booking_url": "https://cal.com/jane-salon", "vertical": "personal_services"}) -> then schedule_appointment({"smb_id": "<from_above>", "action": "book"}) user: "Schedule with this dentist: https://www.doctolib.fr/dentiste/paris/jean-dupont" -> call import_booking_url({"booking_url": "https://www.doctolib.fr/dentiste/paris/jean-dupont"}) user: "Reserve a table at https://www.opentable.com/r/acme-bistro" -> call import_booking_url({"booking_url": "https://www.opentable.com/r/acme-bistro", "vertical": "restaurants"}) WHEN TO USE: Call this FIRST whenever the user provides a specific booking URL (cal.com/handle, calendly.com/handle/event, doctolib.fr/..., booksy.com/..., opentable.com/r/..., etc.). User patterns that match: 'book me at https://cal.com/...', 'schedule with calendly.com/jane/intro', 'reserve a table at opentable.com/r/...', 'I want to book this dentist: https://www.doctolib.fr/...'. After importing, the returned smb_id can be passed straight to schedule_appointment. WHEN NOT TO USE: Do not use if the user only describes a business by name without a URL — call find_business instead. Do not use for arbitrary websites that are not on the supported booking-platform list (use /supply/platforms to see all 12). COST: $0.005 per_call LATENCY: ~600ms

  Connector

• lnt_email_brand_guidelines

  L&T MCP

  SKILL: lnt_email_brand_guidelines Team: Platform L&T Email Brand Guidelines Call this tool to get the complete guide for 'lnt_email_brand_guidelines'. Read the 'content' field and follow its instructions. This tool takes NO parameters. Full content: --- name: lnt_email_brand_guidelines description: L&T brand guidelines for email formatting — reference document, not a function to call with parameters --- # L&T Email Brand Guidelines This is a REFERENCE DOCUMENT. Read it and use the guidelines to construct emails yourself. Do NOT call this with any arguments — it takes no parameters. ## Brand Colors - Primary Navy: #002B5C - Accent Orange: #F47B20 - Body text: #374151 - Light background: #f8fafc ## Email Structure ### 1. Header Block - Background: #002B5C (navy) - White bold text: "L&T Construction" - Subtitle: "EIP Cognitive Services Platform" in rgba(255,255,255,0.65) - Top right: orange badge (#F47B20) with text "MCP AGENT" - Below header: 4px solid orange line (#F47B20) ### 2. Greeting - "Dear [RECIPIENT_NAME]," - Color: #002B5C, bold, font-size: 16px - Padding: 32px top and sides ### 3. Body Content - Font-size: 14px, color: #374151, line-height: 1.7 - Padding: 12px 32px 24px 32px - For plain text: wrap each paragraph in p tags with margin-bottom: 12px - For structured data: use a table with navy (#002B5C) header row, white text, alternating white and #f8fafc rows - End with: "Please feel free to reach out if you need any clarification." ### 4. Divider - 1px solid #e5e7eb horizontal line ### 5. Signature Block - "Warm regards," in #374151 - Sender name in bold #002B5C, font-size: 15px - "L&T Construction — EIP Cognitive Services" in #64748b, font-size: 12px - Padding: 20px 32px ### 6. Footer Block - Background: #f8fafc - Border-top: 1px solid #e5e7eb - Centered text, font-size: 11px, color: #9ca3af - Line 1: "This email was generated by the L&T MCP Agent Platform." - Line 2: "Larsen & Toubro Limited · Construction Division · EIP Cognitive Services" - Line 3: Orange square ■ + "Confidential — For intended recipient only" ## HTML Wrapper - Full document: <!DOCTYPE html> to </html> - Body background: #f4f4f4 - Center everything in a 620px wide white table - White card with box-shadow: 0 2px 8px rgba(0,0,0,0.08) - Border-radius: 8px - All CSS must be inline — no external stylesheets ## Key Rules - From address is ALWAYS lntcs@lntecc.com - Always generate complete valid HTML - Orange accent bar between header and body is mandatory - Generate the HTML yourself from these guidelines — do not call any tool for HTML generation

  Connector

• calculate_buildable_envelope

  ReadyPermit Property Intelligence

  Calculate the maximum buildable area (building envelope) for a lot given zoning constraints. USE WHEN: user asks 'how much can I build', 'max square footage', 'what's the buildable area', 'calculate the envelope', 'how big can my house be', or has specific lot dimensions and zoning rules they want to model. RETURNS: max buildable square feet, max number of stories, envelope dimensions (length × width × height), usable footprint, and coverage math. Takes lot area, setbacks, FAR, height limit, and coverage as inputs — a pure calculation tool, does not query data.

  Connector

• ai-image-gen

  The Stall

  Generate an AI image from a text prompt using DALL-E 3. Returns a public URL for the image (hosted for 1 hour) plus the model's revised prompt. Supports vivid or natural style, and three aspect ratios: square (1024×1024), portrait (1024×1792), or landscape (1792×1024). $0.080/image — 20% below closest x402 competitor. Output is base64-encoded PNG or a direct URL depending on response_format.

  Connector

• search_comparable_sales

  ReadyPermit Property Intelligence

  Find recent comparable property sales and rental comps near a property. USE WHEN: user asks 'what are comps in this area', 'recent sales near here', 'what did similar houses sell for', 'price per square foot', 'market value estimate', 'rental comps', or needs comparable sales data. RETURNS: subject property AVM, list of recent sales with price, sqft, price/sqft, distance, beds/baths, and rental comps with rent amounts. Also includes local market stats. Useful for investor deal evaluation, CMA, and market analysis.

  Connector

• asterwise_get_chaldean_numerology

  Asterwise

  Reduces a name and birth date through the Chaldean letter-value system and returns name, birth, and combined compound analyses with themes and keywords. SECTION: WHAT THIS TOOL COVERS Chaldean assigns letters values one through eight (nine treated as sacred/unassigned in tradition). Response includes data.system 'chaldean', echoed full_name and birth_date, plus three parallel number objects (name, birth, compound) each with raw compound, reduced root, theme, keywords, interpretation. It does not output Pythagorean Life Path blocks (asterwise_get_numerology_profile) or Lo Shu grids. SECTION: WORKFLOW BEFORE: None — standalone. AFTER: asterwise_get_numerology_profile — compare against Pythagorean cores if needed. SECTION: INPUT CONTRACT name and date forwarded as-is; no local validation. SECTION: OUTPUT CONTRACT data.system (string — 'chaldean') data.full_name (string) data.birth_date (string) data.name_number: raw (int — compound) reduced (int — root) theme (string) keywords[] (string array) interpretation (string) data.birth_number — same shape as data.name_number data.compound_number — same shape; raw combines name and birth SECTION: RESPONSE FORMAT response_format=json serialises the complete response as indented JSON — use this for programmatic parsing, typed clients, and downstream tool chaining. response_format=markdown renders the same data as a human-readable report. Both modes return identical underlying data — no fields are added, removed, or filtered by either mode. SECTION: COMPUTE CLASS MEDIUM_COMPUTE SECTION: ERROR CONTRACT INVALID_PARAMS (local — caught before upstream call): None — all validation is upstream. INVALID_PARAMS (upstream): — None — upstream rejection surfaces as MCP INTERNAL_ERROR at the tool layer. INTERNAL_ERROR: — Any upstream API failure or timeout → MCP INTERNAL_ERROR Edge cases: — Chaldean and Pythagorean numbers disagree by design — never merge blindly. SECTION: DO NOT CONFUSE WITH asterwise_get_numerology_profile — Pythagorean Life Path / Expression stack, not Chaldean compounds. asterwise_get_lo_shu_grid — digit placement magic square, not Chaldean name reduction.

  Connector

• calculate_buildable_envelope

  Buildability™ — Property Zoning & Buildability™ Intelligence

  Calculate the maximum buildable area (building envelope) for a lot given zoning constraints. USE WHEN: user asks 'how much can I build', 'max square footage', 'what's the buildable area', 'calculate the envelope', 'how big can my house be', or has specific lot dimensions and zoning rules they want to model. RETURNS: max buildable square feet, max number of stories, envelope dimensions (length × width × height), usable footprint, and coverage math. Takes lot area, setbacks, FAR, height limit, and coverage as inputs — a pure calculation tool, does not query data.

  Connector

• get_incrementality

  Trillboards DOOH Advertising

  Get incrementality/lift test results for a campaign. Uses Bayesian (Beta-Binomial with 10K Monte Carlo samples) and frequentist (chi-square with Yates correction) methods for causal measurement. WHEN TO USE: - Proving causal DOOH advertising effectiveness - Getting both Bayesian and frequentist significance measures - Seeing treatment vs control group visit rates and lift RETURNS: Array of experiments, each with: - experimentId, type (geo_holdout/ghost_ads/psm), status - treatmentDmas, controlDmas - latestResult: treatment/control rates, lift%, incrementalVisits, pValue, posteriorProbPositive, expectedUplift, credibleInterval Returns empty array if no experiments exist for this campaign.

  Connector

• search_comparable_sales

  Buildability™ — Property Zoning & Buildability™ Intelligence

  Find recent comparable property sales and rental comps near a property. USE WHEN: user asks 'what are comps in this area', 'recent sales near here', 'what did similar houses sell for', 'price per square foot', 'market value estimate', 'rental comps', or needs comparable sales data. RETURNS: subject property AVM, list of recent sales with price, sqft, price/sqft, distance, beds/baths, and rental comps with rent amounts. Also includes local market stats. Useful for investor deal evaluation, CMA, and market analysis.

  Connector

• calculate_cost

  MCP Market Russia

  Calculate estimated construction cost based on real market data from the catalog. Uses average price per m² by material and region from actual company prices and projects. Args: area: House area in square meters (required, e.g. 120) material: Building material (каркас/frame, брус/timber, газобетон/aerated_concrete, кирпич/brick, СИП/SIP). Empty = average across all. region: Region or city name for regional pricing. Empty = nationwide average. floors: Number of floors (1 or 2). 0 = no adjustment.

  Connector

• search_local_experiences

  tickadoo-mcp

  Use this when the user mentions a place, neighbourhood, landmark, or area but does not give exact coordinates. Examples: 'near the Louvre', 'in Trastevere', 'around Times Square', "walking distance from St Paul's Cathedral". Returns experiences matched first by exact venue/neighbourhood, then by city centre fallback. Do not use for general city-wide search; use search_experiences for that.

  Connector