"Home Assistant" matching MCP tools:

• convoinspect

  InsideOut (Riley)

  INSPECTION: View a session's conversation transcript and metadata Returns the full message history (user / assistant / tool turns) plus the session's meta — workflow step, cloud, deployment status, drift state. This is the transcript-reader companion to the other read tools — combine it with: • `convostatus` for the live stack / config / pricing • `tfruns` for deployment history (apply / destroy / plan / drift) • `stackversions` for the stack-version ladder Use it when a user asks 'what did I say earlier?' or you need to retrace why the session ended up where it did. Read-only; never mutates session state. REQUIRES: session_id (format: sess_v2_...).

  Connector

• how_munimji_helps

  HelloBooks AI Agents MCP Server

  Explain how HelloBooks and Munimji (the in-app AI assistant) help a specific business — given a free-text description of the user's own operations. Returns a curated capability knowledge base: business-operation areas (sales, purchases, banking, tax, reports, inventory, payroll, multi-entity, setup), and for each AI capability WHO does the work — `autonomous` (Munimji does it on its own, e.g. OCR extraction, running reports), `approval` (Munimji prepares the entry and you one-click approve before it posts to the ledger, e.g. AI categorization, find-and-match, creating invoices/bills by chat), `assist` (co-pilot, e.g. guided onboarding, voice), or `manual` (a software feature you run yourself). Each capability links to the backing software features. Use this when a user describes their business and asks "how can HelloBooks help me?", "what can the AI do for my shop/practice/agency?", or "what can Munimji do on its own vs what do I approve?". Pass their description in `businessDescription`; optionally filter by `area` or `autonomy`. The AI never posts to a ledger without approval. For the full software catalog call list_features; for pricing call list_plans.

  Connector

• get_priority_insights

  RevenueScope: Japanese EC RPS Benchmarks

  Return the top 3 prioritized, pre-computed DIAGNOSES for the site over the given period — 'what should I act on this week', ranked by revenue impact. Unlike get_site_summary / get_kpi_summary / get_channel_breakdown (which return data), this applies a deterministic rule engine over KPI period-over-period changes, per-channel RPS/ROAS/saturation, and AI-assistant referral growth, and returns ranked findings (revenue-trend swings, high-efficiency channels to scale, over-allocated low-efficiency channels, loss-making/saturated ad channels, revenue concentration risk, emerging AI traffic) — each with a severity (risk/opportunity/watch), the numbers, and a recommended action. The priority judgment is fixed in code (not LLM-generated). site_id is OPTIONAL when OAuth-authenticated. Default period is 30 days; pass period='today'/'7d'/'90d' or a raw day count (1-365). Returns fewer than 3 when fewer rules fire (no padding).

  Connector

• compare_cities

  cityparity — Cost-of-Living & Quality-of-Life Comparison

  Compare two cities for one household: take-home pay, full cost breakdown, the equivalent target salary needed to match source net cash, non-cash lifestyle deltas (vacation, parental leave, healthcare), and a 0-100 quality score on five weighted dimensions. Use this for a head-to-head between two named cities; for a single city call get_city_summary, and to rank many cities call rank_cities. Read-only, no side effects; returns a text summary plus structured JSON. RSU income is NOT a parameter; RSU is treated as source-only because grants typically do not follow you across employers.

  Connector

• axint.templates.list

  Axint

  List all 26 bundled reference templates in the Axint SDK. Returns a JSON array of { id, name, description } objects — one per template. Templates cover messaging, productivity, health, finance, commerce, media, navigation, smart-home, and entity/query patterns. No input... Use: use to discover valid template ids before templates.get. Effects: read-only template metadata; writes no files and uses no network.

  Connector

• searchProducts

  dm-drogerie-markt

  Search for products available in the German dm-drogerie market (online and local stores). USE WHEN: searching dm-drogerie products by name, category, ingredient, property, or any natural language query (any language supported). Often answers questions about ingredients and properties directly. Covers: dm-drogerie markt brands, make-up, skincare, perfume, hair, health, nutrition, baby & child, household, home & living, photo, and pets. OUTPUT: Returns a maximum of 15 products. GTIN, DAN, brand, title, details, category, price, appLink (direct product URL), description, highlights/USPs, and extensive attributes including: - Dietary/Allergen: vegan, vegetarian, bio, glutenFree, lactoseFree, sugarFree, nutFree, soyFree - Cosmetic Ingredients: fragranceFree, alcoholFree, parabenFree, sulfateFree, preservativeFree, dyeFree, oilFree, siliconeFree, naturalCosmetics - Product Properties: waterproof, new, limitedEdition, sellout, onlineOnly, exclusiveDm, dmBrand, purchasable NOT FOR: nutritional information (calories, protein, carbs, fats), complete allergen lists, full ingredient details. For these, use 'getProductDetails' tool with the GTINs or DANs. LIMITATIONS: Only make claims based on EXPLICITLY stated product highlights/descriptions. Do NOT extrapolate or assume properties not mentioned in the results.

  Connector

• best_price

  AgentsPrice

  Verified genuine best price for a product category across real sellers: returns the lowest price, the venue offering it, how many sellers were compared, the savings vs the most expensive seller, and a live link to buy. Prices are never fabricated. Categories: electronics, gaming, home, fashion, crypto, travel, clearance, all. Needs an AgentsPrice API key (get one at https://agentsprice.com), passed as api_key. For a no-key sample of what is live now, use list_live_deals.

  Connector

• dossier_web_surface

  drwho.me

  Core dossier check: Snapshot a domain's public web surface: robots.txt, sitemap.xml, and the home-page <head> metadata (title, description, OpenGraph, Twitter cards). Use for SEO audits, content discovery, or verifying metadata before sharing; for HTTP headers use dossier_headers, for redirect behavior use dossier_redirects. Fetches /, /robots.txt, and /sitemap.xml concurrently via HTTPS, 5 s each; parses <head> with a lightweight HTML parser. Returns a composite CheckResult: {status:"ok", meta:{title, description, og, twitter}, robots, sitemapPresent} or {status:"error", reason}.

  Connector

• list_store_categories

  agentView

  Lists all published agentView store categories (e.g. Gastronomie, Wartezimmer, Empfang, Smart Home) with localized titles, descriptions and template counts. Use this to narrow a subsequent search_store_templates call when the user asks for 'templates for a waiting room' or similar. No authentication required. Returns count, language and a categories array where each entry has slug, title, description, templateCount, heroIconKey and detailPath.

  Connector

• analyze_record

  Senzing

  Get the Senzing JSON analyzer script to validate mapped data files client-side. REQUIRED: `workspace_dir` (writable directory, e.g. ~/sz-workspace) — the call WILL FAIL without it. The analyzer validates records against the Entity Specification, examines feature distribution, attribute coverage, and data quality. Returns a Python script (no dependencies) with instructions. No source data is sent to the server. Typical workspace_dir values: Linux `/tmp` or `~/sz-workspace`; macOS `~/sz-workspace`; sandboxed envs: explicit path under home (do NOT assume /tmp exists).

  Connector

• calculate_home_affordability

  AVnester — Indian Real Estate Intelligence

  Estimate the monthly home-loan EMI / monthly payment in India — a home-loan calculator. Deterministic math; not advice or a loan-approval claim. Two modes: pass propertyValue (80% LTV assumed) OR loanAmount for a specific loan (e.g. "₹50 lakh loan"). Use for "what would my EMI be" / "monthly payment on …". The response `assumptionNote` states the basis in plain words. Always surface the disclaimer field.

  Connector

• request_solar

  Utilify

  Capture a Texas homeowner's interest in rooftop solar and route to a licensed installer — use when the user owns (or is buying) a Texas home and mentions solar panels, solar quotes, solar savings, or reducing their bill through solar. Use when the user says 'I just bought a house in Austin and want solar quotes', 'how much could solar save on my Houston electric bill', or 'connect me with a solar installer for my new home'. Returns a lead ID and confirms next steps; Utilify routes the lead to installer partners (SunPower, Sunrun, Palmetto, and independent TX installers). Caveats: (1) only call when the user has explicitly opted in and confirmed homeownership — this is not for renters, and Utilify may earn a referral fee. (2) Texas-only — for non-TX addresses, decline and explain. (3) Don't double-call for the same address in one conversation; one lead per opt-in. If the user has only expressed mild curiosity ('I'm thinking about solar someday'), answer the question first and only call this tool once they confirm 'yes, connect me'.

  Connector

• page.theme.update

  Create Web Page

  Apply a partial theme patch. Theme fields are enum-constrained (button variant/radius/shadow, font family/weight, density, icon_size). Use presets.list first if the user wants a complete restyle. For already-published pages, this saves an unpublished latest revision only. Do not call page.publish in the same assistant turn after this edit. Stop and tell the user the draft/preview was updated, then wait for a separate user message that explicitly asks to update the live link, publish, or make the changes public before calling page.publish. Do NOT call page.unpublish either — the live page should stay public; only unpublish when the user explicitly asks to take it down.

  Connector

• register_agent

  prxhub

  TIME-CRITICAL + HUMAN-IN-THE-LOOP. The device code returned by this tool expires in 10 minutes (600 seconds). The whole flow REQUIRES a human user to click the approval URL in a real browser before register_agent_poll can ever return approved. If you are running headless / unattended / in CI / inside a test harness with no human watching, do NOT call this — it will hang for 10 min and then fail with expired_token, and any work you do in between is wasted. Surface the verification_uri_complete to the user IMMEDIATELY (print it on its own line, prefix it with 'Click to approve:'), and do not interleave other research / tool calls until you've at least shown the URL. DO NOT CALL THIS BLINDLY. Before calling register_agent, check for an existing identity on disk. The lookup order is: 1. $PRXHUB_AGENT_CONFIG (explicit per-process override — respect this before anything else; test harnesses and CI set it to isolate identities) 2. $XDG_CONFIG_HOME/prx/agent.json 3. $HOME/.config/prx/agent.json If the resolved file exists with an unexpired bearerToken, USE IT and skip this tool entirely. Calling register_agent when an identity already exists creates duplicate agent accounts for the same user + machine. Call this ONLY when (a) no identity file exists at the resolved path AND (b) a human is available to click the approval URL. Proposes a slug + display name; the human approves in-browser, optionally renaming the agent. Returns a device code + a pre-filled approval URL. Then call register_agent_poll to wait for approval. Agents do NOT hold signing keys. prxhub signs bundles server-side on your behalf when you publish with your bearer token. ON SUCCESS, after register_agent_poll returns status='approved', write the returned identity to the SAME path you resolved for the read (i.e. $PRXHUB_AGENT_CONFIG if set, else $XDG_CONFIG_HOME/prx/agent.json, else $HOME/.config/prx/agent.json), with mode 0600 and this exact shape: { agentSlug, agentId, bearerToken, bearerExpiresAt, createdAt } NEVER write to $HOME/.config/prx/agent.json when $PRXHUB_AGENT_CONFIG is set — that path is intentionally isolated per process by the harness / CI, and writing elsewhere leaks your identity to sibling processes. ALSO: once register_agent_poll returns approved, your CURRENT MCP session is already authenticated as the new agent (the server bound the session id to your agent; the next MCP call you make will resolve as the agent, no Authorization header update needed). The agent.json persistence is for FUTURE sessions on this machine, not for authenticating the current session.

  Connector

• list_covered_events

  Crosswire

  Free discovery of everything check_resolution_risk can audit: the covered canonical World Cup events, their per-outcome pair ids (…#home / #draw / #away), the Polymarket conditionIds and Kalshi tickers with outcome labels for each pair, match dates, the frozen ruleset_sha pinning the identity graph, the coverage kickoff cutoff, and snapshot freshness. Use a returned pair_id (or a pair's two market ids) as input to check_resolution_risk.

  Connector

• scout.market_pulse

  Scout

  Public-data-backed market snapshot for any US zip code. Returns Census ACS demographics (population, median household income, median age, owner-occupancy %, median home value, median gross rent), Scout's indexed agent density for that zip, and listings activity if the zip is in our MLS-live coverage area. Call this when an AI user asks 'what's the market like in [zip/city]'. Free, no API key required.

  Connector

• place_call

  Call For Me

  Place an outbound phone call to a US business or person. The A.I. assistant on the call will identify itself as A.I., follow your instructions, and return a structured outcome via get_call_status. USE THIS TOOL WHEN: the user wants to make a phone call, contact a business by phone, ask about hours/pricing/availability, book a reservation, gather info that's not online, follow up on a service request, or do any task that requires talking to a human on the phone. LIMITATIONS: - US phone numbers only (E.164 starting with +1). International is not yet supported. - English language only. - Cannot call emergency services (911, 988, etc.) — these will be rejected. - The A.I. will NOT commit to bookings/payments without user confirmation unless safety.must_confirm_with_user is explicitly set to false. - Default 5-minute call duration cap. Returns immediately with a call_id. Poll get_call_status(call_id) for the result.

  Connector

• optimize_home_loan_tax_regime

  AVnester — Indian Real Estate Intelligence

  Compare a home-loan borrower's income tax under the OLD vs NEW regime (FY2026-27) and recommend which regime saves more income tax. Pure deterministic slab math — not tax advice. Use when the user asks "old or new tax regime", "home-loan tax benefit", or "section 80C / 24(b) deduction". Models §24(b) interest + §80C principal (+ joint-loan doubling); the response lists benefits it does NOT model (capital gains, HRA, etc.). Always surface the disclaimer field.

  Connector

• add_ssh_key

  BorealHost

  Inject your SSH public key into a site's container for direct SSH access. The key is appended to /home/admin/.ssh/authorized_keys. Only available for VPS/dedicated plans. Requires: API key with write scope. Args: slug: Site identifier public_key: SSH public key string. Supported types: ssh-ed25519, ssh-rsa, ecdsa-sha2-nistp256/384/521 Returns: {"success": true, "message": "SSH key added", "ssh_command": "ssh admin@184.107.x.x"} Errors: VALIDATION_ERROR: Invalid or unsupported key format FORBIDDEN: Plan does not support SSH

  Connector

• block.update

  Create Web Page

  Patch one content block by stable blockId. Provide a props patch (merged into existing props) and/or a new type. Block types and props are validated against the strict per-type schema. For already-published pages, this saves an unpublished latest revision only. Do not call page.publish in the same assistant turn after this edit. Stop and tell the user the draft/preview was updated, then wait for a separate user message that explicitly asks to update the live link, publish, or make the changes public before calling page.publish. Do NOT call page.unpublish either — the live page should stay public; only unpublish when the user explicitly asks to take it down.

  Connector