The MCP tool directory.

Fetch full article content from a linux.do post URL

Fetch content from a public HTTP(S) URL (supports Markdown files and normal web pages)

Generates a presigned URL for uploading a file to S3. This endpoint handles deduplication by checking if a file with the same MD5 hash already exists.

Find products with the highest agent readiness scores — products that are easiest for AI agents to integrate with. Sorted by compositeScore desc; supports skip/limit pagination. All readiness scores are 0-100, higher better. Calibration: <30 = not agent-ready (default minimumScore filter), 30-49 = early/limited, 50-69 = decent, 70-89 = strong, 90+ = exceptional. Response: array of { slug, name, tagline, websiteUrl, tier (free|verified|featured), unverified (true on free only), verifiedAt (ISO; nullable), agentReadiness: { compositeScore, apiScore, protocolScore, sdkScore, integrationScore, dxScore } (each 0-100), mcp?: { hasMcpSupport, totalToolCount, serverCount } }. Note: ordering is by agent-readiness, not by tier — this is the one MCP tool where tier doesn't reorder results, since the buyer intent is technical fit, not paid placement.

Detect responsive layout breakpoints for a URL. Scans viewport widths from 320px to 1920px and identifies where significant layout changes occur (large height jumps, content reflows). Returns a list of detected breakpoint widths.

Discover login/sign-in pages for a website. Checks the site's sitemap.xml and probes common login URL paths. Returns a list of candidate login URLs found. Use this before attempting to log in to a site.

Find B2B SaaS products that support a specific capability — an integration with a named service ('salesforce-integration'), a data format ('xrechnung-support'), an industry standard ('eclass-support'), or a compliance certification ('soc2'). Accepts either a canonical capability slug or natural language; resolves to a structured capability when possible. Returns products ranked by tier (Featured > Verified > Free). Response: { capability, matchType (none|exactSlug|canonicalSlug|nlpFallback — exactSlug & canonicalSlug are deterministic; nlpFallback is heuristic), resolvedFeatures[], products[] }. Each product: { slug, name, tagline, websiteUrl, tier, unverified (true on free only), verifiedAt, evidence[] (per-claim: featureSlug, evidenceUrl, notes, source, confidence) }. Empty: { capability, matchType, message, suggestedSlugs[] } when no capability matched, or products: [] when capability matched but no products claim it yet.

Return REUSE, REFETCH, or UNKNOWN before retrieving a URL again.

Insert an image from a URL at a specific position in the document.

Generate an AI image from a text prompt using Claude Imagine credits. Returns the image URL.

Generate a PlantUML diagram with automatic syntax validation and error reporting for auto-fix workflows. Returns embeddable image URLs for valid diagrams or structured error details for invalid syntax that can be automatically corrected. Optionally saves the diagram to a local file.

Gets a list of advisory notices for the Supabase project. Use this to check for security vulnerabilities or performance improvements. Include the remediation URL as a clickable link so that the user can reference the issue themselves. It's recommended to run this tool regularly, especially after making DDL changes to the database since it will catch things like missing RLS policies.

Return every verified person who recommends a given book, with quotes and original source URLs.

Return every verified person who recommends a given book, with quotes and original source URLs.

Get the full content of a single chat (one AI engine's response to one prompt on one date). Returns: - messages: the user prompt and assistant response(s) - brands_mentioned: brands detected in the response with their position - sources: URLs the model retrieved, with citation counts and position - queries: search queries the model issued - products: product gallery entries extracted from the response - prompt: { id } - model: { id } Use list_chats to discover chat IDs for a project.

Returns the URL where users can configure this MCP server - adding, editing, or removing actions. Provide this URL to users who want to customize their available tools.

Returns the URL where users can configure this MCP server - adding, editing, or removing actions. Provide this URL to users who want to customize their available tools.

Get the status of a GitHub Copilot coding agent job. Use this to check if a previously submitted task has completed and to get the pull request URL once it's created. Provide the job ID (from create_pull_request_with_copilot) or pull request number (from assign_copilot_to_issue), or any pull request you want agent sessions for.

Get one Dplooy Data collection: its field schema, rows, public URL, and the canonical fetch snippet.

Get a report on source domain visibility and citations across AI search engines. Results are aggregated for the entire date range by default. Use the "date" dimension for daily breakdowns. Returns columnar JSON: {columns, rows, rowCount}. Each row is an array of values matching column order. Columns: - domain: the source domain (e.g. "example.com") - classification: domain type — CORPORATE (official company sites), EDITORIAL (news, blogs, magazines), INSTITUTIONAL (government, education, nonprofit), UGC (social media, forums, communities), REFERENCE (encyclopedias, documentation), COMPETITOR (direct competitors), OWN (the user's own domains), OTHER, or null - retrieved_percentage: 0–1 ratio — fraction of chats that included at least one URL from this domain. 0.30 means 30% of chats. - retrieval_rate: average number of URLs from this domain pulled per chat. Can exceed 1.0 — values above 1.0 mean multiple pages from the same domain are retrieved per conversation. - citation_rate: average number of inline citations when this domain is retrieved. Can exceed 1.0 — higher values indicate stronger content authority. When dimensions are selected, rows also include the relevant dimension columns: prompt_id, model_id, tag_id, topic_id, chat_id, date, country_code. Dimensions explained: - prompt_id: individual search queries/prompts - model_id: AI search engine (e.g. chatgpt-scraper, gpt-4o, gpt-4o-search, gpt-3.5-turbo, llama-sonar, perplexity-scraper, sonar, gemini-2.5-flash, gemini-scraper, google-ai-overview-scraper, google-ai-mode-scraper, llama-3.3-70b-instruct, deepseek-r1, claude-3.5-haiku, claude-haiku-4.5, claude-sonnet-4, grok-scraper, microsoft-copilot-scraper, grok-4) - tag_id: custom user-defined tags - topic_id: topic groupings - date: (YYYY-MM-DD format) - country_code: country (ISO 3166-1 alpha-2, e.g. "US", "DE") - chat_id: individual AI chat/conversation ID Filters use {field, operator, values} where operator is "in" or "not_in". Filterable fields: model_id, tag_id, topic_id, prompt_id, domain, url, country_code, chat_id.

Read one form endpoint: URL, assignment, active/paused, submission COUNT, notification email, confirmation message, origin rule, and the embed snippet. Submissions themselves are dashboard-only (visitor PII) — this never returns them.

Get hour-by-hour weather forecast for a location in the United States. Perfect for 'What's the hourly forecast?' or 'Will it rain this afternoon in [US location]?' questions. Provides detailed hourly conditions for up to 48 hours.

Get hour-by-hour weather forecast for a location in the United States. Perfect for 'What's the hourly forecast?' or 'Will it rain this afternoon in [US location]?' questions. Provides detailed hourly conditions for up to 48 hours.

Retrieve the classification result for a previously submitted image. Use the identifier returned by classify_image or classify_image_url. Poll this endpoint until the result is available.

Fetch a single Mercury motor by id or slug, including pricing, shaft length, and deep-link URL.

**[REAL-TIME API]** Extract all tags from a specific Danbooru post by ID or URL by querying Danbooru API directly. Use this when: - You want to get ALL tags from a single post in real-time - You need tag categories and counts for a specific post For analyzing tag statistics across multiple posts, use 'get_character_tags'.

Get full details for a product by slug, including MCP integration data and agent readiness scores. Response: { p: { slug, name, tagline, description, websiteUrl, logoUrl, pricingModel, currentScore (0-100), tier (free|verified|featured), unverified (true on free only), verifiedAt (ISO; absent if never crawled), categories[] }, mcp?: { hasMcpSupport, totalToolCount, servers[] }, agentReadiness?: { compositeScore (0-100), aiSummary } }. Errors: { error: { code: 'not_found', ... } }.

Get MCP server setup instructions for a product. Returns available servers, their tools, connection details, and whether they support remote (hosted) access. Response when MCP support exists: { product: { slug, name, websiteUrl, tier, unverified, verifiedAt }, hasMcpSupport: true, totalToolCount, servers[], agentReadiness? }. Response when product exists but lacks MCP: { product: {...}, hasMcpSupport: false, message }. Errors: { error: { code: 'not_found', ... } }.

EDITING A SITE? Call this FIRST — the inventory of everything attached: forms, Data collections (prerendered vs client-only), booking pages, chatbot, with ids and keys, plus an SEO warning when Data is loaded by browser fetch() only. Never infer attachments from the HTML or the live URL.

BEFORE ANY EDIT: read the CURRENT LIVE FILES of a deployed Dplooy project — the clean stored source, the ONLY source of truth for edits. Never scrape the site URL instead: served pages contain Dplooy-injected runtime (chatbot, badge, analytics) that is not part of the source. Call this BEFORE editing an existing site — edit against what is actually stored, never from memory (your memory of the site may be stale or from another conversation). Returns the full file inventory plus the text contents (HTML/CSS/JS). Use listOnly first on large sites, then fetch specific paths. After reading, make changes with update_project_files targeted edits ({ path, oldString, newString }) — never re-emit whole files for small changes, and never full-redeploy to edit (a redeploy replaces the whole site and deletes omitted files). Assigned forms, data, bookings and chatbot survive all edits unchanged.