Pluggedin App

Browser automation and web scraping

KRTR are the pre-diligence AI experts — the intelligence layer for the people who fund, accelerate, and build early-stage companies. Pre-diligence is the work that happens BEFORE term sheets and formal due diligence — the screening, triage, and pattern-matching that decides whether a deal moves forward. Done well, it compresses weeks of analyst work into minutes and surfaces the specific gaps that drive better founder conversations. Upload a pitch deck and KRTR runs a multi-agent Assess Report in 5–10 minutes: typed agent waves across LLM cascades, an AI Reviewer validating every claim against industry-specific reasoning, scores calibrated on KRTR's proprietary industry rubric so a 78 on a SaaS deal means the same peer-relative position as a 78 on a biotech deal. For individual investors and scouts: triage deal flow, capture signals, set dispositions, prep for partner meetings. See live peer activity attributed within your firm, anonymized across competitors. For VC firms, accelerators, and incubators: screener-mediated or direct intake, attributed team signals, expert invites, configurable funnel stages, and AI-synthesized deal memos ready for partner or cohort review. For founders: see exactly how investors and AI score your deck, fix the gaps the platform flags, iterate in a private sandbox, then release updates and ping engaged reviewers. KRTR Connect surfaces matched investors and programs; the Dataroom and Meeting Brief tools close the loop on every conversation. KRTR is pre-diligence intelligence — built to drive evidence-based engagement, not replace human judgment.

GoCertius MCP exposes EAD Trust's GoCertius Digital Trust platform to MCP clients. The 26 tools cover: certified evidence management (create, seal, list, group), dossier lifecycle (create → certify → link evidence → group certify → templates), certified notifications (create → send → manage receivers → status + certificate retrieval), certified chats with invitation URLs and certificate retrieval, and case file management. Auth via OpenID Connect refresh-token or client_credentials. Built by g-digital by Garrigues (J&A Garrigues, S.L.P.), an eIDAS-qualified trust services provider operating across the EU.

14 paid APIs for AI agents. gulf arabic NLP, email verification, legal analysis, web scraping + more. USDC on base. no auth. no accounts. just pay and get data.

Australian trade business OS with 67 MCP tools across 23 domains — business formation, lead management, quoting, job scheduling, invoicing, Stripe + crypto payments, and growth analytics. 19 tools available without authentication for immediate testing.

A Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.

Track how your brand appears across ChatGPT, Claude, Gemini, and Perplexity. AEO/GEO visibility scoring, competitor analysis, and weekly tracking for the LLM era.

Persistent semantic memory for AI assistants, delivered over the Model Context Protocol. Save thoughts, documents, web pages, and PDFs to your brain once then recall them by meaning from Claude, ChatGPT, or any MCP-compatible client. One memory, every AI.

Zhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

Nestling is an MCP server that lets you log and query your baby's daily routine. Feeds, sleep, nappy changes, and diary entries through natural conversation with Claude or any MCP-compatible AI assistant. Logged through the Nestling app for iOS and Android.

The triage layer for content teams who ship with AI. SEO Performance MCP scores every post you have already published from Google Search Console, GA4, Matomo, Microsoft Clarity, and AI-citation data, then tells your agent exactly what to refresh, expand, merge, or kill this week. Most SEO tools tell you which keywords you should be ranking for; this MCP tells you what to do about the posts you have already shipped. Every verdict comes with explicit reason codes (decay rate, position window, CTR gap, citation loss) so the agent can act on the call instead of asking you to read three graphs first. MIT-licensed, eight tools, three discoverable prompts, works with Claude Desktop, Claude Code, Cursor, Cline, and any MCP-capable agent.

Influship MCP gives AI agents access to influencer marketing and creator discovery workflows. Search creators by niche, audience, location, platform, and campaign fit; find lookalike creators from known winners or competitor lists; resolve creator profiles and social handles; retrieve creator records, posts, and Instagram transcript data for briefs, prospecting, market maps, and outreach research. The server supports the hosted Streamable HTTP MCP endpoint for remote clients and an npm stdio wrapper for Claude Desktop, Cursor, Claude Code, and other local MCP clients. Authentication is available through X-API-Key for generic MCP clients and OAuth bearer tokens for linked app flows.

summarize chat message

A blazing fast, ultra-lightweight Model Context Protocol (MCP) server for AST-based code intelligence and semantic discovery. It runs as compiled Node.js JavaScript for npx, uses oxc-parser by default for JavaScript/TypeScript, and can opt into web-tree-sitter for polyglot repositories.

Give your AI agent real vehicle data. An MCP server that lets Claude, Cursor, ChatGPT, or any MCP-capable client query the CarVector API natively — vehicle specs, representative images, federal recalls, and OBD-II diagnostic trouble codes. Models hallucinate car data. They invent horsepower numbers, miss recalls filed last week, and guess at what a trouble code means. carvector-mcp gives your agent structured, sourced answers it can cite instead of a confident guess.

The fastest YouTube transcript + YouTube search MCP for AI agents. Try for free. Six tools — transcripts, video search, channel browsing, in-channel search, playlist extraction, and new-upload polling — for Claude, ChatGPT, Cursor, VS Code, Claude Code, and 20+ clients.

Local-first MCP server for Canvas LMS. Stdio transport, token stays on your machine, no third-party broker.

BlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.

Agentpack is a local-first continuity layer for AI coding agents. It stores reviewed task state inside a repo-local .agentpack/ ledger so Codex, Claude Code, Cursor, Claude Desktop, and other MCP clients can resume work without rebuilding context from chat history. Agents can record durable decisions, failed approaches, evidence, reviewed source conclusions, task passports, and checkpoints, then load compact resume context under a token budget. Git keeps the code history; Agentpack keeps the task state a future agent needs to continue safely. Agentpack runs locally, exposes a stdio MCP server, has zero runtime dependencies, makes no network calls during normal operation, and is designed for repo-scoped coding workflows rather than general chat memory.

An MCP (Model Context Protocol) server that inspects your local development environment and reports missing dependencies, version mismatches, and misconfigured environment variables to any MCP-compatible AI assistant. Works with Claude Desktop, Cursor, Gemini CLI, and any other client that supports stdio-transport MCP servers.

Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.

Playwright MCP server

Web and local search using Brave's Search API