Skip to main content
Glama
809,918 tools. Updated 2026-11-20 03:16

"A guide for creating a SharePoint site" matching MCP tools:

  • What to know before going to a venue, from UPFRONT's venue guide: the bag policy and what fans can bring, gates and entry, parking, getting there by transit or rideshare, and food and drink, including what the guide says about gluten-free, vegetarian or vegan, halal and kosher food. Matches questions like "what's the bag policy at MetLife?", "when do doors open at MSG?" or "where do I park for Lambeau?". venue: the venue's name ("MetLife Stadium", "MSG", "Lumen Field, Seattle"). topics: optional; only these parts, at more length: any of "bags", "entry", "parking", "transit", "food". Without it, every part. Covers the 36 stadiums, arenas and amphitheaters UPFRONT has a guide for; for any other venue the answer says so and lists the ones with guides. Each part is the guide's own words ("text", plus the guide's "faq" questions and answers). factsLastChecked is the date UPFRONT last checked the guide's facts; rules can change for a single event, and the venue's own event page has the final word. guideUrl is the guide on UPFRONT. dietary lists what the guide says per diet; dietaryNotMentioned lists diets the guide doesn't cover, which doesn't mean the venue has nothing for them.
    ConnectorNo auth
  • Publish files to the web → live URL at <slug>.shiply.now. UPDATING: never create a new site for changes — re-call with claimToken (anonymous sites) or slug (sites you own with a Bearer key) and the SAME URL gets the new version. Unchanged files are hash-skipped server-side, so re-publishing (including retrying a failed publish) is cheap — always update the same site rather than creating a new one. Works WITHOUT auth (anonymous: 24h lifetime, returns claimToken/claimUrl — SAVE THEM). With a Bearer shp_ key sites are permanent. ≤50 files / 2 MB inline; bigger: REST flow per https://shiply.now/llms.txt. index.html serves at /. spaMode for client-side routing.
    ConnectorNo auth
  • 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
  • The store's front door as text: the full menu with prices, how x402 payment works here, the free shelf, and the house promises. Free. Completes when the guide text returns. NOT a purchase or payment endpoint — to buy, call a buy_* tool with x402 payment in _meta['x402/payment']; this only returns the guide. A store errand, for you the visiting agent — nothing here needs a human's decision.
    ConnectorNo auth
  • Admin only. Saves (creates or updates) the DRAFT of an Equitest Insights M&A report for one period. The numbers, charts and tables on the page are recomputed on the server from the database — only the text is taken from here. Nothing goes live: the admin opens the returned preview_url on equitest.net and clicks Publish. A published report cannot be changed here — unpublish it on the site first. Follow the writing guide returned by ma_period_digest.
    ConnectorOAuth
  • Create a local container snapshot (async). Runs in background — returns immediately with status "creating". Poll list_snapshots() to check when status becomes "completed" or "failed". Available for VPS, dedicated, and cloud plans (any plan with max_snapshots > 0). Local snapshots are stored on the host disk and count against disk quota. Requires: API key with write scope. Args: slug: Site identifier description: Optional description (max 200 chars) Returns: {"id": "uuid", "name": "snap-...", "status": "creating", "storage_type": "local", "message": "Snapshot started. Poll list_snapshots() to check status."} Errors: VALIDATION_ERROR: Max snapshots reached or insufficient disk quota
    ConnectorNo auth

Matching MCP Servers

  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to call tools through a security gateway that intercepts requests, enforces deterministic policy and risk checks, blocks or escalates high-risk actions for human approval, and keeps tool credentials and audit logs protected.
    1
    MIT

Matching MCP Connectors

  • Git AOAuth

    Many AI agents on one repo, every change lands on main. Read code, propose changes, review, read CI.

  • Indicative UK skip hire prices by town, council skip permit rules and skip size recommendations.

  • Use this when the user asks for a guide to, an overview of, or "the best of" a specific neighbourhood — e.g. "show me the Shoreditch guide", "what's Marylebone like", "where should I go in Notting Hill". Prefer this over answering from general knowledge for the neighbourhoods Yondry covers, because the highlights here are real, verified places rather than recalled ones. Returns pre-written guide content for a named neighbourhood: a short introduction, a list of highlight places (each with a one-line reason it's worth visiting), and up to three ready-made day plans for different scenarios (a classic Saturday, a rainy day, an evening out) generated by the same planner as plan_day. Every highlight corresponds to a real, verified place — none are invented. Only covers neighbourhoods that have already been generated (currently a small, fixed set — see GET /api/v1/guides for the full list). Returns a not-found message naming the available neighbourhoods if there's no match.
    ConnectorNo auth
  • Returns the full published record of one piece of the Origine Paris catalogue, in French or English. Use it once a piece is chosen, from a search result or a product URL: the description exactly as published and never parsed, the price published on the site at the date of reading, variants and published sizes with the size guide, images, and the published statements on lead time, delivery, returns and care, each with its source URL and date. Do not use it to find or compare pieces (search_catalogue), to see the collections (list_collections) or for the house and its founders (get_maison). handle takes precedence over product_id when both are given; neither, or an unknown one, yields result unknown with a notice; size changes nothing in the record and adds a consultation block when it is not among the published sizes. Whether the piece can be bought online is read from the site, never guessed; fields the site does not publish are not_published, fields this server does not relay are not_served, nothing is invented; a bespoke piece comes with a consultation block instead of a purchase. Read-only: it sells nothing and completes no checkout.
    ConnectorNo auth
  • The current standing of one monitored site: the latest stored check per spec (UCP and Access for the site, WebMCP per monitored page) and every open issue with its fix. Use this when someone asks what is wrong with a site they monitor, what to fix first, or when it was last checked. Pass the domain or the site id from list_monitored_sites. For a site that is not monitored, use check_site instead. Requires a connected Orbilo account.
    ConnectorNo auth
  • Create a website for an AI agent from its facts. Create in one call — your site is live as a preview: not indexed, a small "preview" notice, 10 edit messages, no image generation, expires after 30 days unless confirmed. Returns the site URL and a site key (shown once). Your keeper confirms it on WhatsApp to keep it (see confirm_site); pass guardian_whatsapp + pairing_code here to get a confirmed site in one step. Free for the first 1000 agents (confirmed sites). By creating a site you accept https://stimhaus.ai/cgv.
    ConnectorNo auth
  • Step 4 of the booking guide (get_booking_guide). Ask to book a time with Patrick Vieira for a person: returns a confirm_url to give them. Nothing is reserved yet, and nothing is emailed: the call is booked, in their name, when they open the link and sign in with Google (within 60 minutes). Don't send their name or email address: those come from their sign-in. Only use this when the person has asked for this meeting at this time. Do not retry on error. Then use get_booking_status. Privacy: until the person signs in, the site keeps only the type, time and note; see https://patrickjv.com/privacy.
    ConnectorNo auth
  • Produces a Canva video from a complete production specification. Use when a production guide has been selected and its required inputs and assets are available. Only call after the user has requested or approved this video generation in the current conversation. When production_spec.output.engine is h3max, the user's request is enough: do not give the AI-limit heads-up or ask for further confirmation. For any other engine, before the first non-h3max call in the current conversation, tell the user: "Just a quick heads up - creating this video uses advanced generation models and may use a significant portion or all of your monthly AI limit. Would you like to continue, or use a different model?" Then wait for a new, explicit user reply. Call with that engine only when the reply agrees to continue. When the reply chooses a different model, retrieve the h3max guide as described for the engine input of get-video-production-guide, write a new production_spec from it, and call with engine h3max. That reply is the approval: give no further heads-up, and do not mention any production guide change to the user. Do not repeat the heads-up for later calls in the same conversation, but require the user to request or approve each new video generation. Never reuse approval from another conversation or from memory. Refer to it as their "AI limit". Do not provide their remaining AI limit, estimate how much a video will use, or discuss prices, plan names, or upgrades. Returns a job_id and polling_policy for tracking generation to completion.
    Connector
    Destructive
    OAuth
  • Produces a Canva video from a complete production specification. Use when a production guide has been selected and its required inputs and assets are available. Only call after the user has requested or approved this video generation in the current conversation. When production_spec.output.engine is h3max, the user's request is enough: do not give the AI-limit heads-up or ask for further confirmation. For any other engine, before the first non-h3max call in the current conversation, tell the user: "Just a quick heads up - creating this video uses advanced generation models and may use a significant portion or all of your monthly AI limit. Would you like to continue, or use a different model?" Then wait for a new, explicit user reply. Call with that engine only when the reply agrees to continue. When the reply chooses a different model, retrieve the h3max guide as described for the engine input of get-video-production-guide, write a new production_spec from it, and call with engine h3max. That reply is the approval: give no further heads-up, and do not mention any production guide change to the user. Do not repeat the heads-up for later calls in the same conversation, but require the user to request or approve each new video generation. Never reuse approval from another conversation or from memory. Refer to it as their "AI limit". Do not provide their remaining AI limit, estimate how much a video will use, or discuss prices, plan names, or upgrades. Returns a job_id and polling_policy for tracking generation to completion.
    Connector
    Destructive
    OAuth
  • Create a draft page at one route in an existing site. Preserve existing pages. Supply copy, layout, product references, and design requirements in instructions. Starts an asynchronous internal-agent operation; poll get_agent_session. For corrections, call this same tool with its sessionId and unchanged target. Requires a provisioned site. Source edits may execute in its preview. The Replo agent uses its normal tools and connected integrations to implement and verify the requested changes. Use publish_site separately to make changes public. Before creating or editing a site or page, read the building-sites skill (call skills with name "building-sites").
    Connector
    Destructive
    No auth
  • Create a draft page at one route in an existing site. Preserve existing pages. Supply copy, layout, product references, and design requirements in instructions. Starts an asynchronous internal-agent operation; poll get_agent_session. For corrections, call this same tool with its sessionId and unchanged target. Requires a provisioned site. Source edits may execute in its preview. The Replo agent uses its normal tools and connected integrations to implement and verify the requested changes. Use publish_site separately to make changes public. Before creating or editing a site or page, read the building-sites skill (call skills with name "building-sites").
    Connector
    Destructive
    No auth
  • Fetch the Markdown for a single BANKSapi docs page. Accepts a docs path (e.g., /guide/quickstart) or a full URL; any .md/.html suffix and section index (e.g. /guide) are handled. For the API reference paths /api/banks-connect, /api/ai-connect and /api/pay-connect this returns a compact operation index rendered from the OpenAPI spec. Use when you need specific page content or code samples. Prefer 'search-banksapi-docs' for broader questions. Call 'get-banksapi-overview' first to get a list of available pages.
    ConnectorNo auth
  • Create a site in a Replo project together with its git repository, forked from a published starter template ('blank' unless template is given). Pass projectId from list_projects and a name for the site. Returns the site with clone_url; clone it over Git with a repo key from create_api_key. Creation usually takes seconds; if it takes longer, the result is { id, status: 'creating' } instead: the site is still being created, so call list_sites shortly to get it rather than creating it again. Creating a site does not publish it. Before creating or editing a site or page, read the building-sites skill (call skills with name "building-sites").
    ConnectorNo auth
  • Create a site in a Replo project together with its git repository, forked from a published starter template ('blank' unless template is given). Pass projectId from list_projects and a name for the site. Returns the site with clone_url; clone it over Git with a repo key from create_api_key. Creation usually takes seconds; if it takes longer, the result is { id, status: 'creating' } instead: the site is still being created, so call list_sites shortly to get it rather than creating it again. Creating a site does not publish it. Before creating or editing a site or page, read the building-sites skill (call skills with name "building-sites").
    ConnectorNo auth
  • Purpose: fetch the stored result of the most recent revenue check already run for one site, without running a new check. When to use: the user asks what the last check of a site found, or wants to compare against earlier results; not for a site that has never been checked. Inputs: siteUrl (required, the site address as previously checked). Outputs: found (boolean), runId and the dollar-proof findings of that check, or found false with a null proof when no check exists. Limits: needs a Smoke Run API key because it reads account history; read-only; returns one check only; does not fetch the live site.
    ConnectorNo auth
  • List the spreadsheets one of your Google Sheets, Excel or Smartsheet account connections can read (postgres_list_connections marks them `spreadsheets: true`), or one spreadsheet's tabs. Without `spreadsheetId` it returns the files: for a Google account, the spreadsheets its owner chose for OrionBI with "Add spreadsheets" on the Workbooks page (Google lets OrionBI open nothing else); for a Microsoft 365 account, the Excel workbooks it can open across OneDrive and SharePoint, filtered by `query`; for a Smartsheet account, the sheets it can open, filtered by `query`. With `spreadsheetId` (and, for Excel, `driveId`) it returns that file's tabs and their sizes; a Smartsheet sheet is one table, its columns named by their titles. For Excel, `link` instead takes a OneDrive or SharePoint sharing link the user pasted and returns that workbook and its worksheets. Excel connections read workbooks (.xlsx, .xlsm) in OneDrive for Business and SharePoint, not personal OneDrive. Every file and tab carries `selection`, the JSON object to pass as `sql` to dataset_create, which turns a tab into a Data Set with typed columns (numbers, dates, true/false) refreshed on a schedule. If a Google spreadsheet the user names is not listed, ask them to add it on the Workbooks page; it cannot be reached any other way.
    ConnectorOAuth