MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Open-source customer messaging for teams with many products: e-mail, live chat and in-app conversations in one inbox, plus newsletters, cookieless analytics, status pages, a help center, a roadmap and a changelog. MCP server for AI assistants. Pre-alpha.
go AGPL-3.0 ★ 30 -
whatsapp-mcp-serverupdated this year
MCP Server for WhatsApp Business Cloud API - Let AI agents send messages, manage contacts, and handle customer support through WhatsApp
npm MIT -
manychat-mcpgithub.com/fabienbutz/manychat-mcpupdated this year
MCP server for the ManyChat API - subscribers, tags, custom fields, flows, messaging
-
pylon-mcp-servergithub.com/gasconc/pylon-mcp-serverupdated this year
MCP Server for Pylon API - Accounts, Issues, Messages, Custom Fields, Tasks, Projects & Milestones
-
A custom MCP server for editing UI messages.
npm ISC -
A phone call MCP server for puch.ai enables users to trigger AI-driven phone calls to customers right from WhatsApp. Instantly place calls, get live transcriptions, summaries, and automate reminders or support all within chat. This bridges messaging and voice for smarter, seamless customer engagement.
-
MCP Server for send text/markdown message via dingding (aka dingtalk) group custom robot
npm MIT ★ 12 -
mcp-brazegithub.com/delta-and-beta/mcp-brazeupdated this year
MCP server for Braze customer engagement platform. 92 tools for users, messaging, campaigns, analytics, and more.
-
WhatsApp Messaging with MCP & Ollama This project integrates PraisonAI Agents with Ollama (llama3.2) and a Go-based WhatsApp bridge. It allows you to send WhatsApp messages using natural language through a local REST API, powered by an LLM and custom MCP tools.
MIT -
WhatsAppMCPgithub.com/samueljayasingh/WhatsAppMCPupdated this year
The WhatsApp MCP Server enables sending and receiving WhatsApp messages, including text and media, through a custom REST API, with all data stored securely in a local SQLite database.
MIT ★ 3 -
Unofficial MCP server for Particular ServiceControl: let AI agents query and act on failed messages, heartbeats, custom checks, sagas and monitoring
MIT -
This project is designed to summarize emails using a custom IMAP client to connect to the user's email inbox and retrieve relevant messages based on specified criteria.
-
Custom Telegram MCP server + TUI auto-responder for Claude Code — 10 MCP tools, SQLite message store, access control, reaction support
AGPL-3.0 ★ 1 -
AIStickyNotesgithub.com/Valectric/AIStickyNotesupdated this year
A tiny utility for leaving AI-readable messages inside your Unity scenes. Add note to a GameObject, and let your AI tools understand your world from the inside via Unity MCP custom tools (https://github.com/CoplayDev/unity-mcp).
MIT ★ 1 -
This repository provides a multi‑purpose MCP (Message Control Protocol) server implementation that can be used as a foundation for building custom communication services. It includes a lightweight server core, extensible plugin architecture, and example client utilities.
-
Know your agent stopped working before your customer does. Alerts on missing activity, failure streaks and undelivered messages from a JSONL event log. CLI, library, and MCP server. Zero dependencies.
npm MIT -
wecom-crm-mcpgithub.com/andyleimc-source/wecom-crm-mcpupdated this year
WeCom (Enterprise WeChat) External Contact MCP Server — a Python SDK and Model Context Protocol server covering the full 客户联系 API surface: customers, tags, group chats, moments, mass messaging, transfer-on-handover, statistics.
pypi MIT -
taste-filipino-mcpactive
Connect Claude Code to Taste Filipino: manage B2B orders, accounts, shipments, customer messages, the B2C webshop (orders, returns, consumer leads, newsletter), AI ad generation and blog posts with AI cover images, directly from your editor.
npm -
Oktopost-MCPgithub.com/Oktopost/Oktopost-MCPupdated this year
The Oktopost MCP Server provides an AI-ready interface to the Oktopost REST API, enabling secure, structured access to campaigns, messages, posts, media, workflows, and advocacy tools. It serves as a reference implementation and a starting point for building custom MCP integrations with Oktopost.
-
Generate, validate, parse & audit ISO 20022 pacs.008 FI-to-FI Customer Credit Transfer messages from Claude Desktop, Cursor & other MCP clients — 10 tools, scheme-aware CBPR+/HVPS+/Fedwire/CHAPS/T2/SCT-Inst rules. Part of the ISO 20022 MCP Suite.
pypi Apache-2.0 ★ 1 -
Fashion E-Commerce Intelligencegithub.com/alexgenovese/ecommerce-fashion-market-analysisno update data
# Fashion E-Commerce Intelligence MCP Server Empower your AI agents, copilots, and assistants with vertical domain-specific fashion intelligence. Built by [alexgenovese.com](https://alexgenovese.com), this Model Context Protocol (MCP) server provides automated **SEO auditing, category trend research, DTC demand forecasting, CRM segment enrichment, and campaign creative generation**—designed natively for Cursor, Claude Desktop, Claude Code, and any MCP-compatible environment. --- ## ⚡ What It Does | Capability | Without this server | With Fashion MCP | |---|---|---| | **SEO Auditing** | Manual checklists, generic advice | Automated **0-100 score** across 5 dimensions with fashion-specific validation (fit, material, color, season, schema, OG, Twitter Cards). | | **Trend Research** | Generic search queries | Deep category-level trend intelligence (trending keywords, colors, silhouettes, price tiers, market fit, confidence). | | **Demand Forecasting** | Spreadsheets & gut feel | Explainable weighted-rule forecast model: `baseline × trend × media × retention × inventory × seasonality` with backtesting. | | **CRM Segment Enrichment** | Static email lists | Customer segments enriched with trending colors/silhouettes/keywords, audience clusters, and ready-to-send targeted messaging. | | **Campaign Creative** | Standard copywriters per channel | Platform-specific campaign themes, hooks, value propositions, and ready-to-use creative briefs grounded in real-time trend data. | --- ## 🔧 Exposed Tools - `product_seo_audit`: Audit any fashion product listing for SEO best practices, structured schema, meta tags, and fashion relevance (fit, size, material). - `fashion_trend_analysis`: Analyze fashion trend data mapped from search engine and social media queries. *(Receives search data input seamlessly, no API key required)*. - `fashion_category_demand_outlook`: Get a rapid, light demand pulse check for a specific product category in a target market and season. - `fashion_dtc_forecast_analysis`: Generate complete DTC demand forecasts with scenario planning (base/upside/downside) and stock-out/overstock risk analysis. - `fashion_customer_trend_enrichment`: Map trending keywords, colors, and silhouettes onto existing CRM customer segments for targeted email/SMS campaigns. - `fashion_campaign_theme_recommendation`: Recommend conversion-optimized ad campaign themes, hooks, and creative briefs for Meta, Google, TikTok, or Email. --- ## 🔐 Privacy & Technical Features - **No API Keys Required:** All analysis, SEO audits, demand forecasts, and CRM enrichment tools run locally with the data you supply. Upstream search data for `fashion_trend_analysis` uses your existing Tavily MCP server. - **Explainable Outputs:** Every tool returns explicit `assumptions[]`, `dataGaps[]`, and `confidence` scores, so your agent always understands the reasoning behind recommendations. - **Zero-Config Local Cache:** Uses a local SQLite persistence layer (`~/.fashion-mcp/store.db`) to cache snapshots, feature stores, and forecast actuals for backtesting. ## 💻 Local Installation To install this stdio-based server locally via Smithery: ```bash npx smithery install alexgenovese/ecommerce-fashion-market-analysis ```
smithery -
DingTalk ServiceWindow MCP Server - TypeScript implementation for AI assistants with message builder
npm MIT -
rms-testerstale
Model Context Protocol server for Respond.io API integration
npm MIT -
customer-support-agentgithub.com/alex-jb/customer-support-agentupdated this year
Triage user messages → auto-draft replies → HITL queue. L5 of the 7-layer one-person company canon. pip · MCP · MIT.
go MIT ★ 2 -
@meterapp/wabiactive
Wabi CLI: run WhatsApp Business from your terminal or CI. Every Wabi op is a command (sandbox, messages, templates, agents, billing), plus a stdio MCP bridge.
npm MIT -
Centralisez tous vos formulaires au même endroit
AGPL-3.0 -
Desktop notifications, custom sounds, ntfy mobile notifications, email notifications, and API pushes reduce anxiety while waiting for AI tasks, allowing you to comfortably enjoy a cup of coffee.
npm MIT ★ 9 -
Secure MCP server for Front.com: search conversations, manage contacts, send messages, automate inbox workflows — 26 tools, 172 actions.
npm MIT ★ 1 -
convot-mcpupdated this year
MCP server for the Convot public REST API (operate the inbox: conversations, messages, contacts, help center).
npm MIT -
Official Omnifox.io Model Context Protocol (MCP) server — 48 tools over the Omnifox v1 REST API for Claude, Cursor, Continue and any MCP client. Every tool verified end-to-end against a live workspace.
npm MIT -
Wapliss WhatsApp for Perplexity: use your own WhatsApp in Perplexity through the Wapliss MCP server (custom plugin + remote connector)
MIT -
@mseep/ntfy-mcp-serverstale
An MCP (Model Context Protocol) server designed to interact with the ntfy push notification service. It enables LLMs and AI agents to send notifications to your devices with extensive customization options.
npm Apache-2.0 -
Multilingual decision engine for intents you describe in plain words, no training examples. It picks the matching intent, with a margin that flags doubtful answers; R2Intent v1 also answers yes or no (beta), with probabilities. About 26 ms per message on a GPU (compiled). Python, HTTP or MCP, self-hosted. Library Apache-2.0; models CC BY-NC 4.0.
Apache-2.0 ★ 1