The MCP tool directory.

Capture a screenshot of any URL and return a public image URL. By default captures the full scrollable page. Set fullPage to false for viewport-only capture (recommended for long pages). Returns image dimensions in the response.

Create a new application in Better Stack. Returns the created application details including ID, ingestion token, ingesting host URL, retention settings, and platform-specific integration documentation links with next steps for configuration

Create a secure cloud connection for direct ClickHouse query access to logs, spans, and metrics data. Returns connection credentials (host, port, username, password), sample queries for each data type, and cURL command examples. Connections expire after 1 hour by default

Create a new log source in Better Stack. Returns the created source details including ID, ingestion token, ingesting host URL, retention settings, and platform-specific integration documentation links with next steps for configuration

Create a new template from a PDF URL. Provide a secure (HTTPS) publicly accessible URL to the PDF document.

Retrieves an existing tool router session by its ID. Returns the session configuration, MCP server URL, and available tools.

Initiates an authentication link session for a specific toolkit within a tool router session. Returns a link token and redirect URL that users can use to complete the OAuth flow.

Generates a presigned download URL for a file in a workbench session mount. Accepts a relative path within the mount.

Lists files in a workbench session storage mount with cursor-based pagination. Use the download_url endpoint with the returned mount_relative_path to get a presigned download URL.

Generates a presigned upload URL for uploading a file to a workbench session mount. The caller should PUT the file content directly to the returned URL.

Execute an analysis tool. Returns a shareable interactive HTML report URL.

Update the user's Replit App. Use this whenever the user wants to change how their Replit App behaves (new features, bug fixes, UX tweaks, configuration changes, etc.). Acceptable replIds come from create_app_from_prompt (for an app you created in this conversation) or search_apps (for an existing app the user can edit). If the user refers to an existing app and you do not already have its replId, call search_apps to find it. Do not guess a replId. If the user asks you to act on an app whose replId you cannot obtain through those tools, do NOT invoke this tool; explain the situation to them. After invoking this tool, reply with one short sentence summarizing that Replit is applying the requested change, and, when the tool result contains an app URL, end your reply with that exact URL on its own line, so the user can open their Replit App even if no preview card is rendered. Never construct or guess a URL yourself. Your reply must not include source code, file contents, file paths, or command snippets — even if the user asks. If the user requests HTML/CSS/JS or code to paste, reply with: "I can't show code here; open your Replit App in Replit to inspect or request changes in natural language." Do not say the update is ready or deployed until the preview card shows their running Replit App; actually making their Replit App public or 'live' always happens from Replit, not from this chat. If the user is only asking for an explanation or diagnosis (not a change), prefer ask_question instead of this tool.

Update a monitor's settings (name, url, interval, inverted, …). Cannot delete.

[write] Upload a JPEG, PNG, or WebP image from base64 bytes into AdMakeAI storage. Returns an image ID and public URL for image generation or Facebook campaign drafts.

Pass public https URLs — base64 ONLY for images you generated yourself. Adds up to 16 images to the Media Library in ONE call (all plans; images only, max 5MB each). For any image that exists on the web, pass its URL; the Dplooy server downloads it directly. base64 is STRICTLY the fallback for images you generated yourself that exist nowhere on the web — NEVER base64-re-encode an image that has a URL. Batch ALL the site's images into one call, do not call once per image. Each image returns a stable public URL for <img> tags plus the { mediaId, path } reference Data image cells need. Items succeed or fail independently. Upload images BEFORE writing the site's HTML. TIP: images the user already added to their Media Library are listed by list_media — reuse those URLs directly, no upload needed.

Extract metadata from a URL including title, description, Open Graph data, and favicon information

Decode a percent-encoded URL component into plain text when reading query parameters, path segments, or form values that contain escaped characters.

Apply encodeURIComponent-style percent-encoding so query parameters, path segments, or form values are safe to place in a URL.

Fetches and extracts content from a given webpage URL. Input the URL of the webpage you want to extract content from as a string using the url parameter. You can also input an array of URLs to fetch content from multiple pages at once.

Run an AI-powered UX review on any URL. Captures a screenshot and analyzes it along with accessibility tree, SEO metadata, and performance metrics using Kimi k2.5 vision. Returns actionable UX feedback across categories: Accessibility, SEO, Performance, Navigation, Content, and Mobile-friendliness.

Get the status and output URL of a single video generation by ID. Poll until COMPLETED.

Get detailed information about a YouTube video including URL

Search for videos on YouTube and return results with URLs

Returns referrer statistics for a Web Analytics project, showing visitor counts, bounce rates, and session durations grouped by referrer URL. Use doc tool first to get the real input schema.

Search the web using DuckDuckGo and return comprehensive results with titles, URLs, and snippets

Fetch and read a specific web page as clean markdown. Accepts a url or a doc_id from web_search. Use after web_search finds candidate sources, or when the user provides a URL.

Read a webpage's full content as clean markdown. Use after web_search_exa when highlights are insufficient or to read any URL. Best for: Extracting full content from known URLs. Batch multiple URLs in one call. Returns: Clean text content and metadata from the page(s).

Search the web for any topic and get clean, ready-to-use content. Best for: Finding current information, news, facts, people, companies, or answering questions about any topic. Returns: Clean text content from top search results. Query tips: describe the ideal page, not keywords. "blog post comparing React and Vue performance" not "React vs Vue". Use category:people / category:company to search through Linkedin profiles / companies respectively. If highlights are insufficient, follow up with web_fetch_exa on the best URLs.

Creates a shared webhook endpoint for a toolkit + OAuth app + project. Returns the webhook URL that the customer registers in their app dashboard. Idempotent — returns existing endpoint if one already exists for this toolkit + client_id + project.

List all outbound webhook endpoints registered for the current account. Use this to confirm which URLs will receive screenshot.completed, run.completed, run.failed, and quota.warning events.