"A tool for writing product manuals" matching MCP tools:

• system_reliabilityA

  ReliaStatsA

  Given per-component reliabilities and a structure ('series' or 'parallel'), return the system reliability. Series = product (all must work). Parallel = 1 − product(1−Rᵢ) (at least one works). Useful for back-of-envelope RBD calcs before reaching for full RBD tooling. For mixed-structure systems (series with parallel sub-blocks), call this tool repeatedly on the sub-blocks. ANTI-FABRICATION: exact closed-form. Quote verbatim.

  ConnectorNo auth

• get_product_detailsA

  SendaMeal StorefrontA

  Get the details of one or more products. The details are the variants, the options, and the images. Arguments productIds - The list of product IDs. Get these IDs from the 'search_products' tool. Request only the products that the user needs. The server has a maximum count of IDs. The default maximum is 20. If you send too many IDs, the server returns an error. Then send fewer IDs. option_values - The option IDs and the value IDs of one variant. Use this argument with one product ID only. This argument applies to the B2C catalog. For a B2B buyer, the tool returns all the variants. Then select one variant. channelId - Optional. This argument selects the B2B catalog. The default is the channel of the request. variantCursor - Optional. This argument gets the next page of variants. Use this argument with one product ID only. Take the value from 'nextVariantCursor' in the previous result. If 'nextVariantCursor' is absent, or is null, or is the text "null", do not send this argument. Results The tool returns a list of products in 'products'. The output schema gives all the fields. A product has 'modifierOptions' only if the product has modifier options. A variant has a price, an inventory level, a purchase flag, and bulk prices only for a B2B buyer. If the tool does not find a product, the list does not include that product. Modifier options A modifier option is a product choice that is not a variant. Examples are an engraving message and a gift note. A variant option is never a modifier option. If a product has no 'modifierOptions', add the product to the cart without 'selectedOptions'. An option is required if 'isRequired' is 'true'. Send each required option to the 'add_item_to_cart' tool. If you do not send a required option, the server does not add the item. A variant selection does not replace a required option. Each option has 'optionEntityId', 'displayName', and 'selectedOptionsKey'. 'selectedOptionsKey' is the name of the field to send the option in. A choice option has 'values'. Each value has 'valueEntityId' and 'label'. A free-entry option has 'constraints' in place of 'values'. If 'unsupported' is 'true', you cannot send the option. A file upload is one example. If such an option is also required, tell the user to buy the product on the website. Variant pages The list of variants can be one page of a longer list. The server sets the page size. If 'hasMoreVariants' is 'true', more variants exist than the tool returned. Then do not tell the user that a variant does not exist. You did not receive all the variants. To get the next page, call this tool again. Send the same product ID, and only that product ID. Send 'variantCursor' with the value of 'nextVariantCursor'. A filter is better than a page walk. If the user named the variant, send 'option_values' instead. One filtered call is cheaper than many pages. Do not change 'option_values' between pages. The cursor is a position in the list of the previous call. A different filter gives the wrong variants. Stock Each product has 'inStock'. It tells you if the store has units in stock. It does not tell you if the user can buy the product. If 'inStock' is 'false', do not refuse the request. Many stores accept orders for products that are not in stock. Tell the user that the product is not in stock, and that delivery can take more time. Then add the product if the user agrees. If the store blocks the purchase, the 'add_item_to_cart' tool fails and gives a reason. Give that reason to the user. If 'inStock' is 'true', the store reports no out-of-stock condition. A store that does not count stock reports 'true' for all products. Therefore do not tell the user a quantity. 'inventoryLevel' is present only if the store publishes stock counts. If 'inventoryLevel' is absent, the count is unknown. The count is not zero. Each variant has its own 'inStock'. Use the value of the variant if you add one variant. Steps 1. Call the 'search_products' tool to get the product IDs. 2. Call this tool with the product IDs. 3. Call the 'add_item_to_cart' tool with the results of step 1 and step 2. If a product has variants, you must tell the 'add_item_to_cart' tool which variant to add. If a product has required modifier options, you must send those options.

  ConnectorNo auth

• niche_draft_directA

  Niche — Editorial IntelligenceA

  Draft the creator's own take or product straight into posts, with no research scan and no story/angle picks. Use this for product-led or bring-your-own-content work: a specific thing to say ('new walnut dining table, live edge, $2,800') or a page to repurpose. The signal pipeline (niche_signal_scan) is for 'what's worth writing about my niche'; this is for 'write this exact thing.' Provide at least one of: `take` (what to say), `source_url`, or `source_text` (the last two repurpose an existing page). Returns a session_id in under 2s; poll niche_session_state(wait:30, wait_until:'checkpoint') to cp3_awaiting_review/complete, then read outputs[]. Pass `brand_id` to bind the creator's voice, offer, and call to action so the draft sounds like them and includes their offer (set those first via niche_brand_profile_set).

  ConnectorNo auth

• nexbid_purchaseA

  discoveryA

  <tool_description> Initiate a purchase for a product found via nexbid_search. Returns a checkout link that the user can click to complete the purchase at the retailer. The agent should present this link to the user for confirmation. </tool_description> <when_to_use> ONLY after user has expressed clear purchase intent for a specific product. Requires a product UUID from nexbid_search or nexbid_product. ALWAYS confirm with user before calling this tool. </when_to_use> <combination_hints> nexbid_search (purchase intent) → nexbid_purchase → present checkout link to user. After purchase → nexbid_order_status to check if completed. Use checkout_mode=wallet_pay when the user has a connected wallet with active mandate. </combination_hints> <output_format> For prefill_link (default): Checkout URL that the user clicks to complete purchase at the retailer. For wallet_pay: Intent ID and status for mandate-based authorization. Include product name and price for user confirmation. </output_format>

  ConnectorNo auth

• getProductDetailsA

  dm-drogerie-marktA

  Retrieve detailed product information for dm-drogeriemarkt products. USE WHEN: ingredients, nutrition facts, allergens, usage instructions, warnings, hazard info, product URLs/images INPUT: DANs (7 digits, preferred) and/or GTINs (8-14 digits) multiple products can be requested at once min 1 / max 50. Use search tool first if only product name is known. OUTPUT: TOON format (compact YAML-like). Fields: name, brand, description, ingredients, nutrition, allergens, usage, warnings, URLs, images. found=false for unresolved IDs. NOT FOR: prices, availability, stock, reviews, recommendations ERRORS: validation error if >50 or no identifiers

  ConnectorNo auth

• get_full_productA

  Moltline Creator StudioA

  Load one product in full: its persona plus every paid skill. PREMIUM (license). Typical input {"slug": "brand-voice"} returns {"slug": ..., "name": ..., "persona": "<persona text>", "skills": [{"name": ..., "instructions": ...}, ...], "free_skill": {...}}. Returns persona plus every skill for one product. Use when the caller wants the whole product. Not for a single skill (get_full_skill) and not for a free look, which list_products and get_free_skill provide with no plan. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "unknown slug '<value>'"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• voice_fingerprintA

  Moltline Humanizer — Voice-Matching EditorA

  Build a measurable voice profile from samples of a person's real writing. FREE. Feed it 2+ samples (emails, posts, essays — 150+ words total) and use the result with humanize_plan / verify_rewrite. Typical input {"samples": ["<email text>", "<blog post>"]} returns {"label": "my-voice", "target_metrics": {"avg_sentence_len": ..., "burstiness": ..., ...}, "favorite_words": [...], "signature_habits": ["..."], "words_analyzed": N}. Use on samples the person actually wrote, to build a target profile. Not for scoring an unknown draft (ai_tell_scan) and not on text the person did not write. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "need 150+ words of real writing across the samples"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• get_full_productA

  Moltline Research DeskA

  Load one product in full: its persona plus every paid skill. PREMIUM (license). Typical input {"slug": "thesis-advisor"} returns {"slug": ..., "name": ..., "persona": "<persona text>", "skills": [{"name": ..., "instructions": ...}, ...], "free_skill": {...}}. Returns persona plus every skill for one product. Use when the caller wants the whole product. Not for a single skill (get_full_skill) and not for a free look, which list_products and get_free_skill provide with no plan. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "unknown slug '<value>'"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• get_full_productA

  Moltline Creator StudioA

  Load one product in full: its persona plus every paid skill. PREMIUM (license). Typical input {"slug": "brand-voice"} returns {"slug": ..., "name": ..., "persona": "<persona text>", "skills": [{"name": ..., "instructions": ...}, ...], "free_skill": {...}}. Returns persona plus every skill for one product. Use when the caller wants the whole product. Not for a single skill (get_full_skill) and not for a free look, which list_products and get_free_skill provide with no plan. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "unknown slug '<value>'"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• voice_fingerprintA

  Moltline HumanizerA

  Build a measurable voice profile from samples of a person's real writing. FREE. Feed it 2+ samples (emails, posts, essays — 150+ words total) and use the result with humanize_plan / verify_rewrite. Typical input {"samples": ["<email text>", "<blog post>"]} returns {"label": "my-voice", "target_metrics": {"avg_sentence_len": ..., "burstiness": ..., ...}, "favorite_words": [...], "signature_habits": ["..."], "words_analyzed": N}. Use on samples the person actually wrote, to build a target profile. Not for scoring an unknown draft (ai_tell_scan) and not on text the person did not write. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "need 150+ words of real writing across the samples"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• get_full_productA

  Moltline Research DeskA

  Load one product in full: its persona plus every paid skill. PREMIUM (license). Typical input {"slug": "thesis-advisor"} returns {"slug": ..., "name": ..., "persona": "<persona text>", "skills": [{"name": ..., "instructions": ...}, ...], "free_skill": {...}}. Returns persona plus every skill for one product. Use when the caller wants the whole product. Not for a single skill (get_full_skill) and not for a free look, which list_products and get_free_skill provide with no plan. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "unknown slug '<value>'"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• renderProductTilesA

  dm-drogerie-marktA

  Retrieve dm-drogeriemarkt products and render them as a visual card grid (product image, brand, name, link to the product page). USE WHEN: the user wants to see products, an overview of several products, or a picture/link instead of a text description INPUT: DANs (7 digits, preferred) and/or GTINs (8-14 digits) multiple products can be requested at once min 1 / max 50. Use search tool first if only product name is known. OUTPUT: card grid rendered by the host. found=false for unresolved IDs. NOT FOR: ingredients, nutrition facts, allergens, warnings - the cards do not show them, use getProductDetails for those. Not for prices, availability, stock, reviews, recommendations. ERRORS: validation error if >50 or no identifiers

  ConnectorNo auth

• get_full_productA

  Moltline Catalog — 138 Agent Skills & PersonasA

  Load one product in full: persona plus every skill's instructions. PREMIUM (paid plan). Typical input {"slug": "inbox-zero-assistant"} returns {"slug": ..., "name": ..., "persona": ..., "skills": [{"name": ..., "instructions": ...}], "free_skill": {...}}. Returns persona plus every skill for one product. Use when the caller wants the whole product. Not for a single skill (get_full_skill) and not for a bundle of products (get_full_kit). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "unknown slug '<value>'"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• get_full_productA

  Moltline Educator ToolkitA

  Load one product in full: its persona plus every paid skill. PREMIUM (license). Typical input {"slug": "curriculum-architect-hs"} returns {"slug": ..., "name": ..., "persona": "<persona text>", "skills": [{"name": ..., "instructions": ...}, ...], "free_skill": {...}}. Returns persona plus every skill for one product. Use when the caller wants the whole product. Not for a single skill (get_full_skill) and not for a free look, which list_products and get_free_skill provide with no plan. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "unknown slug '<value>'"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• get_full_productA

  Moltline Educator ToolkitA

  Load one product in full: its persona plus every paid skill. PREMIUM (license). Typical input {"slug": "curriculum-architect-hs"} returns {"slug": ..., "name": ..., "persona": "<persona text>", "skills": [{"name": ..., "instructions": ...}, ...], "free_skill": {...}}. Returns persona plus every skill for one product. Use when the caller wants the whole product. Not for a single skill (get_full_skill) and not for a free look, which list_products and get_free_skill provide with no plan. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "unknown slug '<value>'"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• get_full_productA

  Moltline StudioA

  Load one product in full: persona plus every skill's instructions. PREMIUM (paid plan). Typical input {"slug": "inbox-zero-assistant"} returns {"slug": ..., "name": ..., "persona": ..., "skills": [{"name": ..., "instructions": ...}], "free_skill": {...}}. Returns persona plus every skill for one product. Use when the caller wants the whole product. Not for a single skill (get_full_skill) and not for a bundle of products (get_full_kit). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "unknown slug '<value>'"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• lookup_authoring_skillA

  kernelcadA

  Return the kernelcad-authoring SKILL.md body — conventions for writing .kcad.ts scripts (imports, parameters, evaluation contract, common pitfalls). Use this tool BEFORE generating CAD code if your MCP client does not list resources. Clients that do list resources should instead read `kernelcad://skills/authoring` directly — the contents are identical. INPUT: none. OUTPUT: { uri, mimeType, text } where `text` is the SKILL.md body.

  ConnectorNo auth

• get_boundary_geojson_simplifiedA

  BoundrA

  Fetch simplified GeoJSON for a boundary by its ONS census code. Safe to embed directly in generated HTML map files. At the default tolerance (0.0001°) a constituency polygon shrinks from ~4,000 vertices to ~200–400 with no visible difference at normal map zoom levels. Prefer this over get_boundary_geojson_by_code() when writing Leaflet map pages — the full geometry is large enough to exhaust your context window before you can finish writing the HTML.

  ConnectorNo auth

• get_full_productA

  Moltline Personal SuiteA

  Load one product in full: its persona plus every paid skill. PREMIUM (license). Typical input {"slug": "inbox-assistant"} returns {"slug": ..., "name": ..., "persona": "<persona text>", "skills": [{"name": ..., "instructions": ...}, ...], "free_skill": {...}}. Returns persona plus every skill for one product. Use when the caller wants the whole product. Not for a single skill (get_full_skill) and not for a free look, which list_products and get_free_skill provide with no plan. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "unknown slug '<value>'"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• get_full_productA

  Moltline Business SuiteA

  Load one product in full: its persona plus every paid skill. PREMIUM (license). Typical input {"slug": "smb-ops-desk"} returns {"slug": ..., "name": ..., "persona": "<persona text>", "skills": [{"name": ..., "instructions": ...}, ...], "free_skill": {...}}. Returns persona plus every skill for one product. Use when the caller wants the whole product. Not for a single skill (get_full_skill) and not for a free look, which list_products and get_free_skill provide with no plan. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "unknown slug '<value>'"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• updateSkillRevisionFileA

  Duvo MCPB

  Write a text file into a skill revision. Writing into a draft leaves the active revision untouched until the draft is promoted; writing into the active revision changes what the skill runs immediately. Historic revisions are read-only: create a draft from one to edit it.

  Connector

  Destructive

  No auth