MCP Servers & Tools

Agentic search over your team's uploaded documents, answering questions only from those sources.

Best for: Teams that need Q&A restricted strictly to their own uploaded documents

One REST key for profile, post, comment and product data across 20+ social and commerce platforms.

Best for: Teams pulling data from several social networks at once

Chrome extension for Option-clicking a UI element and sending it to Claude Code as debugging context.

Best for: Developers using Claude Code who debug UI issues in the browser

Open-source shared workspace where teams build agents and automations through chat, with tracing, evals and versioned configs.

Best for: Teams that want shared, scheduled AI agents with approvals and an audit trail

Anthropic's coding agent that reads a repository, edits files and runs commands from the terminal, IDE, desktop app, browser or Slack

Best for: Developers who live in the terminal and want an agent that runs tests and opens PRs rather than suggesting lines

Desktop agent workspace that runs work off your calendar and connects to thousands of tools over MCP

Best for: People whose work is already organised around meetings and deadlines

Open-source visual builder for LLM agents and RAG flows, deployable as an HTTP API or an MCP server.

Best for: teams prototyping RAG and agent flows visually before coding them

Describe a workflow in plain English and it builds the automation, backed by Paperform's integration library.

Best for: Small businesses wanting workflow automation without learning a node-based builder first

Connects AI agents to over 1,000 apps and tens of thousands of actions through one credential layer.

Best for: Developers already using multiple MCP-compatible agent clients who want one shared set of app connections

Hosting and a CMS that a coding agent can drive over MCP or an API, publishing real React sites.

Best for: Letting a coding agent ship and maintain a site end to end

Gives AI agents authenticated, rate-limited access to over 1,000 external tools and apps through one API.

Best for: Developers building AI agents that need to take real actions in external apps, not just chat

Local context gateway that picks, filters and logs what files and tool output reach your AI coding agent or app.

Best for: Developers using coding agents who want to cap and audit the context they send

LinkedIn outreach agent that picks prospects from post activity and drafts the messages; now branded Linxa.

Best for: Solo founders and small sales teams doing LinkedIn outreach by hand today

A board of AI agents that write and QA code, send outreach and post on social, running on your own Claude subscription.

Best for: Solo technical founders on a Claude subscription who want agents working tickets overnight

Gives each AI coding agent its own persistent cloud computer — disk, shell, and network — reachable via MCP from Claude Code or Cursor.

Best for: Developers running long test suites, migrations, or scheduled jobs through a coding agent

CRM with AI search, call recording and natural-language workflow building baked into the data model.

Best for: startups whose pipeline does not fit a stock CRM schema

Builds a persistent map of what a codebase does and exposes it to engineers and AI coding agents.

Best for: Enterprises modernizing or maintaining legacy systems with sparse documentation

Groups customer requests from calls, tickets and CRM into ranked projects and code-aware specs, then tracks the work from code and tickets

Best for: Product leads who spend their week reassembling customer demand and project status

Generates and keeps code documentation, tests and diagrams in sync with a connected Git repository.

Best for: Engineering teams that want documentation to stay current automatically, not just generated once

Personal AI workspace that keeps one long-term memory of your work, people and plans and shares it across several AI models.

Best for: People who use several AI assistants and want one shared memory between them

Local desktop app that categorises bank CSVs on your machine and exposes them to Claude, ChatGPT or Cursor over MCP

Best for: People who refuse to hand bank credentials to an aggregator

A self-hosted proxy that checks role, redacts fields and logs every request an AI agent makes against databases, files and APIs.

Best for: Platform and security teams putting agents in front of production databases

Open-source desktop chat app that runs open models offline or connects to cloud providers, plus a terminal coding agent.

Best for: Privacy-focused users who want an offline ChatGPT-style app

AI agents that turn plain-language DevOps requests into deterministic incident-response and provisioning workflows.

Best for: Platform teams wanting AI-assisted incident response tied to a real Kubernetes cluster

AI layer inside Miro's whiteboard: agents that read the canvas, cluster stickies and run prebuilt playbooks.

Best for: teams that already run workshops in Miro

Source-available multimodal retrieval engine that embeds whole document pages, so RAG works over diagrams and datasheets.

Best for: Engineering and manufacturing teams searching technical manuals and datasheets

Interviews you about a feature, then writes constitution, requirements, solution and task files

Best for: Developers using Claude Code, Cursor or similar who want a spec before generation

Email, SMS and web push marketing for online stores, with AI forms, reports and product recommendations on the paid plans.

Best for: Shopify and WooCommerce stores running email plus SMS

Open-source social scheduler for 30+ networks, with a public API, MCP and self-hosting.

Best for: Agencies and creators who want an exit from Buffer-style lock-in

Cuts long videos into captioned vertical clips and dubs them into 80+ languages, driven by API, CLI or MCP

Best for: Podcast and webinar teams cutting a weekly long-form episode into shorts

Trains a support chatbot on your docs and help center, then embeds it on the site or in Slack

Best for: Support teams with existing documentation they want to make answerable

Web data API that searches, scrapes, crawls and interacts with sites, returning clean Markdown or JSON for LLM pipelines.

Best for: Developers feeding site content into RAG or agent pipelines

Describe an app to Claude or ChatGPT and Floot builds, hosts and deploys the full stack.

Best for: Non-developers who already work inside Claude or ChatGPT

Chat-based creative agent that picks image, video and audio models for each step of a brief and assembles the result.

Best for: Marketers producing matched sets of ads, product shots and short videos from one brief

Turns your docs, tickets and wikis into a question-answering agent that cites its sources and answers inside Slack, Jira or Zendesk.

Best for: internal IT or HR helpdesks with a large document corpus

Builds custom B2B prospect lists by searching 200+ live sources, then enriches them with verified contacts.

Best for: Building niche prospect lists based on specific criteria beyond firmographics

Self-hosted open-source runtime that serves text, speech, vision, image and agent workloads behind OpenAI-compatible APIs.

Best for: Teams that must keep inference on their own infrastructure

Memory layer for AI agents and apps that stores user facts and preferences between sessions and retrieves them on demand.

Best for: Developers adding per-user memory to chatbots, support agents or assistants

A shared board where an AI agent drafts marketing campaigns as cards for a human to steer and approve.

Best for: Solo marketers or small agencies running campaigns for several clients

Proactive AI teammate with persistent memory that works through iMessage, Slack, email and the web, and builds routines for repeat tasks.

Best for: Founders and operators who want one assistant across iMessage, Slack and email

Generates game-ready pixel art sprites, animations, and tilesets from text prompts, exportable to major engines.

Best for: Solo or small-team game developers needing placeholder or production sprite art fast

Open-source Postgres backend with auth, storage, realtime, edge functions and a pgvector toolkit for AI apps.

Best for: Developers and vibe-coders who need a ready backend with auth for a web or mobile app

Security workers that review pull requests, red-team code and guard AI agents' inputs and actions, free for open-source repositories.

Best for: Open-source maintainers who want free automated PR security review

Context layer that links code, chats, tickets and docs so coding agents and developers get reliable answers and better pull requests.

Best for: Engineering teams with long-lived codebases and scattered tribal knowledge

Writes, narrates, captions and edits short or long videos from a prompt, then schedules them to your social accounts.

Best for: running a faceless short-form channel across several networks

Brand and category research data — social, ads, audience, trends — queried from Claude or ChatGPT, or via API.

Best for: Agencies pulling together a new-business pitch on a deadline

Screenshots a landing page, scores it against 60 conversion criteria and returns annotated fixes ranked by impact.

Best for: Founders auditing their own landing page before paying for traffic

Visual Tailwind builder: generate a page with AI, edit it by hand, export React, Vue or plain HTML

Best for: Building Tailwind marketing pages faster than hand-writing the classes

Chat-driven video editor inside Wistia that cuts multi-source footage into recaps, reels and social clips.

Best for: Marketing teams already hosting video on Wistia

Open-source GenBI agent that answers data questions in plain language and builds dashboards over your governed warehouse data.

Best for: Data teams exposing warehouse data to Claude, ChatGPT or internal agents over MCP

Open-source tool that keeps specs, issues and agent runs inside your git repo so coding agents can hand context to each other.

Best for: Developers running several coding agents in parallel on one codebase

LinkedIn outreach agent that builds an ICP from your business, finds matching prospects and sends up to two messages each.

Best for: Solo founders doing their own outbound on LinkedIn

Meeting transcription with per-plan minute and length caps

Best for: Teams that live in Zoom, Meet or Teams and want notes without a note-taker