MCP server for tidying a large Outlook / Hotmail mailbox via Microsoft Graph. Bulk moves, folder-tree surgery, inbox rules — no send tool, no permanent delete.
22 consolidated MCP tools for email, calendar, contacts, folders, rules, categories, and settings with safety controls (dry-run preview, rate limiting, recipient allowlists) and MCP annotations on every tool. Works with personal Outlook.com and work/school Microsoft 365 accounts.
Enables AI agents to read, search, draft, send, reply to, forward, and organize Microsoft Outlook mail via Microsoft Graph, with safe-by-default read-only operation and browser-based sign-in.
Enables read-only access to personal Microsoft Outlook mail, calendar, and contacts via the Microsoft Graph API using device-code authentication, without requiring the Outlook desktop app.
Local-first Microsoft Outlook MCP server: a single Go binary that manages calendar events and mail through the Microsoft Graph API over stdio, with tokens stored in the OS keychain and no Entra ID app registration required. Exposes four aggregate tools (calendar, mail, account, system) dispatched by an operation verb, with multi-account support and read-only and mail-gating modes.
Enables AI apps to connect Microsoft Advertising accounts, read campaigns and reports, and save campaign changes as drafts that only go live after approval.
Two AIs. One answer. ChatGPT and Claude discuss with each other until they agree, through your own signed-in CLIs: no API keys. Both read your project (never change it) and search the web. Plugin for Claude Code, Codex, Claude Desktop and the ChatGPT app.
A Model Context Protocol (MCP) server for Microsoft Advertising (Bing Ads / DuckDuckGo Ads). This server enables AI assistants to create, manage, and report on Microsoft Advertising campaigns programmatically.
Lets a Claude Code session on one Mac run tasks in Claude Code on another Mac over Tailscale. Tools start, follow, list and cancel resumable headless sessions, with token auth and allowlisted folders.
Multi-agent swarm orchestrator for AI workflows. Exposes blackboard read/write, agent dispatch, permission gating (AuthGuardian), token budget enforcement (FederatedBudget), and audit log tools over MCP. Supports 14 AI framework adapters including LangChain, AutoGen, CrewAI, Codex, and A2A — mix any frameworks in one swarm with race-condition-safe shared state.(Traffic light for agents)
.FAF (Foundational AI-context Format) with 50+ tools - Only Persistent project context that integrates seamlessly with Claude Desktop workflows. Officially merged (#2759) Anthropic MCP server.
Check whether a website is visible to AI search engines (ChatGPT, Perplexity, Claude, Google AI Overviews). Returns a 0-100 readiness score, a grade, and a specific fix for each gap. Dependency-free, no API keys.
An MCP server that gives orchestrator agents fine-grained control over interactive Claude Code sessions running inside tmux, enabling mid-session steering, interruption, and token-efficient result extraction.
Privacy-preserving authentication cookie security auditing for AI browser agents, MCP clients, and automated testing. Detects missing HttpOnly, Secure, SameSite, and other cookie protections, and returns structured security findings without exposing raw cookie values.
A licensed, locally run Playwright E2E testing MCP server for Claude Desktop and Cursor. It lets AI coding agents inspect semantic accessibility structure, validate role-based browser flows with explicit assertions, and generate reusable Playwright tests.
Lets Claude Desktop and Claude Code inspect and drive Windows desktop applications in the background, including clicking, typing, launching, and verifying results, while the user keeps their mouse, keyboard, and foreground window.
Post-hoc session handoff and project memory for Claude Code: MCP tools list_sessions and handoff turn any session — even crashed or usage-limit-hit ones — into a clean handoff.md another model can continue from, with secrets redacted from every output. Zero dependencies, fully local; also distills a project's entire session history into one cited memory brief.
Enables healthcare AI interactions via MCP protocol with built-in EU AI Act compliance. Provides quick installation, well-documented API, and enterprise support.
Enables interaction with biometrics AI features, including risk management, transparency, bias detection, and compliance tracking, all compliant with the EU AI Act.
Enables Claude Code to maintain a persistent todo list stored in SQLite, with tools to list, search, add, update, complete, and delete todos across sessions.
Connect Claude Duet to Claude Code: an MCP connector that lets Duet start Claude Code sessions, talk to your open terminal windows, and get answers back. Remote MCP server on Cloudflare Workers + a Claude Code channel.
Enables AI agents to program MicroPython boards such as Raspberry Pi Pico and ESP32 through Thonny, with visible shell commands and optional human approval.
Chat with Claude right inside Blender: describe what you want, and it builds, edits and checks your scene while you
watch.
Claude Bridge adds a Claude tab to the 3D View sidebar. Type a request like "a cozy living room with a sofa, a
coffee table and a warm floor lamp" and Claude places the objects at real-world sizes, assigns materials, sets up
lights and a camera, then looks at the re
An integration that allows Claude Desktop to interact with Spotify, enabling users to control playback, search music, manage playlists, and get recommendations through natural language commands.
Manage Proxmox VE from Claude through a desktop app for Windows and Linux: guests, snapshots, backups, consoles and files, with per-host Off / Ask / On permission switches and an approval window for each request.
MCP server that provides browser automation capabilities through a Chrome extension, enabling terminal-based agents to interact with any website via a live browser session with optimized context.
Lets Claude list, add, update, and remove your claude.ai connectors from chat, and set per-tool Always allow or Needs approval permissions. It drives your own signed-in Chromium session because claude.ai exposes no public API for this.
A group chat for AI agents. Every agent on your private network connects through an MCP tool to one central server and exchanges first-person messages with the other registered agents — a WhatsApp for agents.
An MCP gateway that connects an owner's existing AI assistant to Estonian business back-office work: company profiles and obligation calendars built from public register data, job playbooks, curated connector catalogue, and server-enforced approvals with receipts. It lets a micro-entrepreneur's chat assistant read deadlines, check counterparties and draft filings while blocking any action that lacks an approval bound to the exact recipient, amount and document.
Enables searching and retrieving Claude Code conversation history via hybrid semantic and keyword search, allowing the agent to access its own past interactions.
Relays messages between two Claude Code sessions running on separate machines, using the Channels API to push an incoming message directly into the other session so one session can ask another about its own checkout. Each message carries an id and is tracked as sent, delivered-to-process, or answered, with a per-message reply budget.
Free, MIT-licensed MCP testing harness with Jay: risk-based testing workflows, exploratory and regression checks, accessibility investigation, bug triage, disposable demos, and protected local evidence reports. Runs locally via @testers-ai/carbon-mcp; the coding agent supplies model, browser, and shell access, and analytics defaults off in the npm edition.
Enables agents to estimate the water and energy consumed by chat prompts, a year of usage, or an entire agent session from its token counts, returning everyday comparisons along with the accounting boundary, assumptions and methodology version behind each figure.
Enables AI assistants to query system health, metrics, service reconnaissance, run multi-node patrols, and send incident alerts across distributed infrastructure through MCP tools.
Connects Claude Code with multiple AI models (Gemini, Grok-3, ChatGPT, DeepSeek) simultaneously, allowing users to get diverse AI perspectives, conduct AI debates, and leverage each model's unique strengths.
Query multiple AI models (GPT-4, Claude, Gemini, Grok) in parallel for diverse perspectives. Get different expert viewpoints when stuck or need enhanced reasoning.
Enables Claude to recall and query past conversations through a local knowledge graph and vector index, with tools for searching memory, retrieving related entities, and adding new memories.
BeforeTheChart AI is a $79 local trading MCP server for Claude Desktop and Cursor. Analyze Marketaux stock and cryptocurrency news sentiment with timestamps and sources, then calculate deterministic risk-based position sizes. Decision-support only—no trade execution, investment advice, or return promises.
Enables two-way communication between Claude Code and clew, allowing message passing and command execution via MCP tools or native peer mesh with auto-reply support.
An MCP server that reads a file's embedded C2PA Content Credential to report whether it declares AI generation or a real-world capture, and checks whether that declaration's signature still verifies against the file's current bytes.
Records privacy-preserving receipts for AI-assisted tasks and enables optional onchain reward claiming via AIPOU tokens. Integrates with MCP-compatible clients like Claude and Cursor.
Provides AI-powered educational tools for teachers including lesson planning, quiz creation, student progress analysis, learning path recommendations, and rubric generation. Enables educators to automate administrative tasks and personalize learning experiences through natural language interactions.
Enables AI clients to analyze any company domain and determine its AI maturity tier (commercialized, deployed, declared, or none) with supporting evidence, via a single tool backed by an Apify actor.
Connect AI agents to Jev AI (jev-ai.pro) for classification, scoring, yes/no checks, advisory action assessment, batched typed decisions and saved judges. Returns structured answers and probabilities using your Jev AI API key.