Skip to main content
Glama
704,943 tools. Updated 2026-10-26 11:38

"A guide to coding a monorepo" matching MCP tools:

  • Create new guides Create one or more new guides based on provided queries. Each guide targets exactly ONE engine and ONE analysis mode, chosen with the optional `source` field (default `google`). How to request each guide type: 1. Google SERP guide (1 credit per guide): omit `source`, or pass `source: "google"`. Example payload: {"queries": ["best crm"], "lang": "en-us"} 1bis. Google AI Overview guide (1 credit per guide). Two modes, like AI engines: `source: "google_ai_overview"` builds the guide from the TEXT of Google's AI answers (AI Overview, completed with AI Mode answers) ; `source: "google_ai_overview_citations"` builds it from the content of the web SOURCES those answers cite (recommended for GEO). Same language/country parameters as a Google SERP guide, 1 credit per guide in both modes. Example payload: {"queries": ["best crm"], "lang": "en-us", "source": "google_ai_overview_citations"} 2. LLM ANSWER guide (4 credits per guide): pass the engine name alone, e.g. `source: "chatgpt"`. The guide is built from the answer text the AI generates for the query. Example payload: {"queries": ["best crm"], "lang": "en-us", "source": "chatgpt"} 3. LLM CITATIONS guide (4 credits per guide) [RECOMMENDED AI mode]: pass the engine name with the `_citations` suffix, e.g. `source: "chatgpt_citations"`. The guide is built from the content of the web pages the AI cites in its answer. Example payload: {"queries": ["best crm"], "lang": "en-us", "source": "chatgpt_citations"} Which AI mode to pick? For GEO (getting a page visible in AI answers), prefer `<engine>_citations`: AI engines send traffic by CITING pages as sources, so the winning move is to look like the pages they cite. The answer-text mode (`<engine>` alone) is mostly useful to analyze how the AI phrases its own answer. When in doubt, pick `<engine>_citations`. The same two modes exist for every AI engine (chatgpt, perplexity, claude, gemini, grok, mistral, deepseek). To optimize the same page for several engines or modes (e.g. Google AND ChatGPT answers AND ChatGPT sources), create one guide per source value on the same query. IMPORTANT, HOW TO READ THE RESPONSE OF THIS ENDPOINT, WHICH SPENDS CREDITS. Queries listed in `guidesFailed` are PROVEN not to have produced a guide and their credit was given back (unless the account has unlimited credits, where nothing was reserved): re-sending them is free and correct. Queries listed in `guidesUnknown` have an UNDECIDABLE outcome and their credit is deliberately KEPT, because the guide was most likely written: DO NOT re-send them, you would pay for the same guide twice. Look them up in `GET /api/v1/guides` after a few minutes instead, and contact support if nothing shows up. Finally, a `200` is NOT a promise that every query produced a guide: compare `guides.length` with the number of queries you sent, never read `success` alone, and never re-send a query just because it is missing from `guides`.
    ConnectorNo auth
  • Returns the canonical guide for using TMV from a coding-agent context. Covers the fix-test-retest loop, how to write a good test prompt, how to read the actionTrail / consoleErrors / failedRequests outputs, and common gotchas. Call this first if you're a new agent on a project — it'll save you a debug session. The same content is served at https://testmyvibes.com/docs/coding-agents.
    ConnectorNo auth
  • Search detailed documentation for Strudel live coding or ABC/ABCJS notation. Returns relevant code examples and explanations from the official docs. Use this when the curated guides (get-strudel-guide, get-music-guide) don't cover what you need — for specific functions, advanced techniques, or when you're unsure about syntax. Powered by semantic search over strudel.cc and ABCJS docs.
    ConnectorNo auth
  • Returns an official GuruWalk support guide for a specific traveler-support topic. GuruWalk is a platform for free walking tours and paid activities; these guides are GuruWalk's own source of truth on how bookings, cancellations, account settings and contacting guides actually work, including current policies and the exact URLs travelers should use. These guides apply only to bookings and accounts on guruwalk.com. Available topics: - account_settings: The traveler wants to manage their GuruWalk account: edit their details (name, surname, phone, city, password), change their email, stop receiving emails / unsubscribe, or delete their account; or they can't access their account. These are concrete steps you shouldn't improvise: consult this before answering. - contact_guru: The traveler wants to contact or coordinate something with the guide of their GuruWalk booking, or thinks they are talking directly to the guide: they can't find them at the meeting point, the guide didn't show up, they're running late, they treat you as if you were the guide, ask for the tour photos, or ask about bringing a pet or paying the guide, or have a question only the guide can answer. - free_tour_modification: The traveler wants to modify or reschedule their GuruWalk free tour — change the day, time, language or number of people — or asks how to do it. - group_booking: The traveler wants to book or extend a GuruWalk booking for a group (they usually say how many; treat it as a large group from around 6 people), asks how to book for many people, can't book for the whole group, sees a large-group notice or is asked for a card or payment for the group, or had a booking cancelled as "group or duplicate". The rules aren't intuitive; consult this before advising. - paid_cancellation: The traveler wants to cancel or change a paid activity booked on GuruWalk, asks about a refund, or can't cancel from their account. Call this when the traveler raises a support topic covered above. Pass the exact topic; the guide content is returned.
    ConnectorNo auth
  • Mamanida's editorial buying guides for one storefront, in that storefront's own language. Called without `guide` it lists the published guides (metadata only: title, deck, meta description, pillar, topics, dates and the canonical Mamanida URL), optionally filtered by `topic`. Called with `guide` (the guide slug from the listing) it returns that one localized edition plus its structured body: paragraphs, headings, lists, comparison tables, callouts, links to other guides and category calls-to-action. A `category_cta` gives a `category_slug` you can pass straight to search_products, which is the intended guide → category → product path. Retailer and affiliate URLs are never returned.
    ConnectorNo auth
  • The published guides. With no slug: the list, newest first, each with its title, description, written date and address, optionally only those whose title, description or slug contain every word of q. With a slug: that guide in full, its body as markdown. A guide that is not published is not found.
    ConnectorNo auth

Matching MCP Servers

  • A
    license
    Not graded
    quality
    B
    maintenance
    面向 Codex、WorkBuddy 等 AI 工具的知你AI助手合并版 Skills,涵盖当前会话分诊、客户查询与画像、历史会话检索、客户分群和 API Key 用量查询,并连接个微、企微、视频号、微信小程序、公众号、服务号、微信客服、微信小店、抖音号、小红书、微博、网站及H5客服等渠道。
    MIT No Attribution
  • A
    license
    Not graded
    quality
    B
    maintenance
    这是面向智能运维场景的 MCP 工具服务,让 Agent 能够按需检索日志内容并获取主机与应用的监控指标数据。它把实时的日志与指标证据接入 Plan-Execute-Replan 诊断流程,从而支撑自动故障排查与根因分析。
    MIT

Matching MCP Connectors

  • Read the full text of a cooking guide from recipes-daily.com, as markdown. Call this when search_recipes lists a guide that answers the question — how or why something works in the kitchen, how to store or substitute an ingredient, how to use a piece of equipment — and answer from what it says rather than from memory, citing its URL. Pass the guide URL exactly as search_recipes returned it. For recipes, use show_recipes instead: a recipe is a page the person cooks from, not text to retell.
    ConnectorNo auth
  • Fetch Yahoo Shopping homepage editorial cards, including title, link, category, and thumbnail. This is a buying-guide and deals feed, not product search; use yahoo_shopping_category for a section, yahoo_shopping_article for one guide, or yahoo_shopping_store for one retailer's offers.
    ConnectorNo auth
  • Fetch Yahoo Shopping homepage editorial cards, including title, link, category, and thumbnail. This is a buying-guide and deals feed, not product search; use yahoo_shopping_category for a section, yahoo_shopping_article for one guide, or yahoo_shopping_store for one retailer's offers.
    ConnectorNo auth
  • <summary>Replace the user's writing style guide for one channel, the voice Sliq writes in there. A set guide overrides the communication style in memory, so when the user wants to sound different in a channel that has a guide, change the guide. It replaces text the user wrote or approved: keep everything they didn't ask to change, and tell them what you changed. To edit a guide, read it with get_writing_style_guide and pass back the whole new guide, without the notes that tool appends after it. The other channels keep their guides.</summary> <returns> <description>The writing style settings after the change.</description> </returns>
    ConnectorOAuth
  • Dependency approval decision for coding agents: decide whether an npm dependency or package is safe to install or adopt and return GO, WARN, or BLOCK using vulnerabilities, security, license, maintenance, deprecation, and package metadata. Price: $0.25 via x402. Generate one _salt19_operation_id per intended purchase, preserve it across retries, and add _x402_payment_signature after satisfying the challenge. A stable _salt19_operation_id is required and makes semantic retries at-most-once. _salt19_operation_id is recommended but optional for standard x402 compatibility.
    ConnectorNo auth
  • Get the guide to authoring a wireframe mockup — the markup dialect, the wireframe component set, what the drawn style discards, and a complete valid example. Call this BEFORE composing your first mockup in a conversation: markup written from general Tailwind and HTML habits is refused, and the guide is what an author needs to write a mockup that is accepted first time.
    ConnectorOAuth
  • Use this when a veteran needs what a VeteranHQ guide on a VA topic says, given a slug from search_guides. A guide states the rules as VeteranHQ read them from the cited sources on the date it reports, and only VA decides a claim. Returns the slug, title and summary, the date the facts in it were last verified against its sources, the public URL of the guide on veteranhq.app, the body split into the sections the guide itself defines, each with a heading and its text, and the sources the guide cites, each with a title and a URL. A slug this library does not hold returns a tool error carrying GUIDE_NOT_FOUND, whose message says to call search_guides and use a slug from its results. A guide longer than one result can carry returns the sections that fit, plus omittedSections counting the sections left out and a note stating that count and the guide URL. A single section larger than the whole budget is served shortened at a paragraph or sentence boundary, with truncatedSection naming its heading and the note repeating it, so a section that was cut is distinguishable from one served whole. Those three fields are absent when the whole guide is returned, so a shortened answer is distinguishable from a complete one. It reads no account data, so the answer is the same for every caller with the same inputs.
    ConnectorNo auth
  • Read the Meridian Dispatch field record for one place: a sight, museum, beach or park, a trail or scenic drive, an event, or a ski resort. Returns the best time to go, how long it takes, effort, season, access, how to get there and what goes wrong, plus the best months, practical answers, a photo, the town guide link and a citation; an event adds its dates and schedule, a trail its route facts. Use it once you know the place. For a whole country or town use get_destination; for a dispatch use get_dispatch; to find a place you cannot name exactly use search_guides; for what else is close use list_nearby. Give url, or name (at least one). A place mentioned on a town guide with no page of its own returns its short write-up and that guide. A URL of a town, country or dispatch page returns that guide instead. Read-only. No match returns an error message.
    ConnectorNo auth
  • Fetch an xTiles guide/documentation document by its `xtiles://guide/...` URI. The same documents are also exposed as MCP resources — use this tool when your client cannot read resources directly. Before generating Markdown for any `*_from_markdown` tool, read `xtiles://guide/markdown/overview` (and `/canvas`, `/collections`, `/blocks`) to get the syntax. `xtiles://guide/markdown/design` holds the colours, styles, layout and tab colours created content takes. `xtiles://guide/markdown/tasks` covers tasks — where a task goes, whose it is, and which dates to set.
    ConnectorOAuth
  • Browse Fly Frugal's published day-by-day budget travel itineraries. Use this to discover which destinations have a guide, then call get_itinerary with a returned slug for one guide's preview. Each item has slug, country_name, tagline, days_count, a preview, cover and first-day image URLs, price_cents and currency for the full guide, updated_at, and pdf_ready. Results are newest first. Only public previews are returned; the paid full guide is never included.
    ConnectorNo auth
  • Return Genpio's guide for one country or market: what that market's platforms allow for an AI livestream host, quoted from their own policies with links, which local platforms Genpio does not stream to, which languages Genpio Voices speaks there, and the guide's full text as Markdown. Use it whenever a question names a country, and pass the language the person is writing in so the guide comes back in it. For a country without a guide it says so and gives only what holds worldwide; do not carry another country's platform rules over to it. With no country, it lists every guide.
    ConnectorNo auth
  • Use when a user asks what a Strong Saga guide recommends, for a guide's top picks in order, or how the picks were ranked. Returns each published buying guide with ranked_list, the guide's full numbered list in its own order read from the guide (rank, name_in_guide, label, id, buy_url; picks whose main guide is another guide carry main_guide), its ranked_picks (id, guide_rank, label, name, price_text, buy_url), other products from the guide outside its numbered list, and how_we_ranked quoted word for word from the guide (null when the guide has none). Pass guide (a slug like best-power-racks-under-500) for one guide, or category (from /categories) for guides covering it. Use get_home_gym_gear with an id for full specs. buy_url is a strongsaga.com/go/ link that opens the retailer: show it to users exactly as given.
    ConnectorNo auth
  • Full use-case detail as a JSON+Markdown envelope: step guide, pros/cons, FAQ, tools used (JSON) + the full narrative guide (Markdown, full_md). null if unknown. Pass `fields` to project to only the keys you need (token-efficient).
    ConnectorNo auth
  • Render a ready-to-paste coding prompt for an annotation, formatted for a target assistant. A deterministic template (no AI spend); for a deeper analysis use diagnose_annotation.
    ConnectorNo auth
  • Buy a city guide for the user, paid inside this conversation. Gives a pay link that takes an MPP payment (a Stripe Shared Payment Token from your wallet, such as Link). Confirm the user's email first: the guide goes to that account, and the purchase is final.
    ConnectorNo auth