AgentRPC
Universal RPC layer for AI agents across network boundaries and languages AgentRPC allows you to connect to any function, in any language, across network boundaries. It's ideal when you have services deployed in: - Private VPCs - Kubernetes clusters - Multiple cloud environments AgentRPC wraps your functions in a universal RPC interface, connecting them to a hosted RPC server accessible through open standards: - Model Context Protocol (MCP) - OpenAI-compatible tool definitions (OpenAI, Anthropic, LiteLLM, OpenRouter, etc.)
Ads
Overview
Universal RPC layer for AI agents across network boundaries and languages AgentRPC allows you to connect to any function, in any language, across network boundaries. It's ideal when you have services deployed in: - Private VPCs - Kubernetes clusters - Multiple cloud environments AgentRPC wraps your functions in a universal RPC interface, connecting them to a hosted RPC server accessible through open standards: - Model Context Protocol (MCP) - OpenAI-compatible tool definitions (OpenAI, Anthropic, LiteLLM, OpenRouter, etc.)
Capabilities
- Invoke registered functions across languages
Ask your assistant to call a function you registered via the AgentRPC SDK, regardless of the language it’s written in.
- Connect to tools inside private networks
Let your assistant interact with functions running in a private VPC or Kubernetes cluster without opening inbound ports.
- Run long-running operations
Trigger function calls that exceed typical HTTP timeouts using the platform’s long-polling support.
- Access tools via hosted MCP
Point your assistant to the hosted MCP server (`npx agentrpc mcp`) to discover and use all your registered tools.
Installation
npx agentrpc mcp
Configuration
{
"mcpServers": {
"agentrpc": {
"command": "npx",
"args": [
"agentrpc",
"mcp"
]
}
}
}Paste into ~/.cursor/mcp.json or .cursor/mcp.json
Tags
- communication
- productivity
Related MCP servers
Communication
ElevenLabs
> [!WARNING] > This local MCP server is deprecated in favor of the ElevenLabs hosted MCP server. > > The hosted server is available at https://api.elevenlabs.io/v1/mcp, with nothing to install or run locally. It authenticates with OAuth, so no API keys are copied into your client. See the hosted MCP server documentation to connect from Claude, Cursor, or any other MCP client. > > This repository is no longer actively maintained. 1. Get your API key from ElevenLabs. There is a free tier with 10k credits per month. 2. Install uv (Python package manager), install with curl -LsSf https://astral.sh/uv/install.sh | sh or see the uv repo for additional install methods. 3. Go to Claude > Settings > Developer > Edit Config > claude_desktop_config.json to include the following:
6 tools · isolate_audio, sound_effects
Communication
Resend Email
Connect your AI agent to the Resend platform. Send and receive emails, manage contacts, broadcasts, domains, and more, directly from any MCP client like Claude, Cursor, or Claude Code. We offer both a remote MCP server hosted by Resend and a local MCP server (this package). Connect any MCP client that supports remote servers (Streamable HTTP). There's nothing to install and no local process to run, which makes it the best option for web-based clients like Claude and hosted agent platforms. When you connect, your client opens a browser window to log in to Resend and approve access using OAuth.
6 tools · add_suppressions, create_contact
Communication
Twilio
This is a monorepo for the Model Context Protocol server that exposes all of Twilio APIs. The Model Context Protocol (MCP) is a protocol for exchanging model context information between AI tools and services. This implementation allows you to expose Twilio's APIs to AI assistants and other tools that support the MCP protocol. This monorepo contains two main packages: - mcp - MCP Server for all of Twilio's Public API - openapi-mcp-server - An MCP server that serves the given OpenAPI spec Each package has its own comprehensive README with detailed documentation:
5 tools · Buy and configure phone numbers, Filter exposed APIs by service
Communication
Mailtrap
An MCP server that provides tools for sending and testing in sandbox via Mailtrap. Before using this MCP server, you need to: 1. Create a Mailtrap account 2. Verify your domain 3. Get your API token from Mailtrap API settings 4. Get your Account ID from Mailtrap account management - MAILTRAP_API_TOKEN - Required for all functionality - MAILTRAP_ACCOUNT_ID - Required for templates, stats, email logs, sandbox list/show, and sending domains. Optional only for the send tools (send-email, send-sandbox-email, and the batch-send-\ tools) and the email campaign tools.
6 tools · Debug delivery with email logs, Inspect sandbox messages
Communication
Mailgun
A Model Context Protocol (MCP) server for Mailgun that gives AI agents a practical, workflow-oriented interface to send email, diagnose deliverability, and manage account operations. > [!NOTE] > This MCP server runs locally on your machine and communicates over stdio. Mailgun does not currently offer a hosted version of this server. - Messaging — Send emails, retrieve stored messages, resend messages - Domains — View domain details, verify DNS configuration, manage tracking settings (click, open, unsubscribe) - Webhooks — List, create, and update event webhooks - Routes — View and update inbound email routing rules - Mailing Lists — Create, view, and update mailing lists and their members - Templates — Create, view, and update email templates with versioning - Analytics — Query sending metrics, usage metrics, and logs - Stats — View aggregate statistics by domain, tag, provider, device, and country - Suppressions — View bounces, unsubscribes, complaints, and allowlist entries - IPs & I
6 tools · Manage domains and DNS, Manage templates, lists, routes, and webhooks
Communication
Integration App
The Membrane MCP Server is a Model Context Protocol (MCP) server, it provides actions for connected integrations on Membrane as tools. Here's our official AI Agent Example that shows you how to use this MCP server in your application. - Node.js (v18 or higher) - A Membrane account To run the development server locally, start it with: The server will be live at http://localhost:3000 ⚡️ Deploy your own instance of this MCP server to any cloud hosting service of your choice. The project includes a Dockerfile for easy containerized deployment.
4 tools · apps, Authenticate with a Membrane token
Communication
Wavix
A Model Context Protocol server that gives LLMs and AI agents direct access to the Wavix telecom platform — SMS/MMS, voice calls, 2FA, SIP trunking, phone-number management, 10DLC registration, call recordings, speech analytics, and billing. Wavix is a global communications platform for sending SMS, placing voice calls, and running 2FA flows over a single API. A free trial is available; paid usage follows the Wavix pricing plan attached to your account. The fastest way to use this MCP server is the hosted endpoint at https://mcp.wavix.com/mcp — point any MCP-compatible client at it and authenticate with your Wavix API key. If you need to self-host (custom Wavix deployment, behind a firewall, dedicated instance), see Run your own.
6 tools · billing_transactions_list, buy_numbers_list
Communication
Sinch Engage / MessageMedia MCP server
This repository contains the source code for the Sinch Engage (Sinch MessageMedia in AU) MCP server, which provides Sinch Engage APIs as MCP tools. Here is the list of tools available in the MCP server (all the phone numbers must be provided in E.164 format, e.g., +61400000000 for Australia). - Node.js >= 16.0 - A provisioned Sinch Engage account - Claude Desktop (or any other MCP client). This README is focused on Claude Desktop, but the MCP server can be used with any MCP client. To use the APIs used by the MCP tools, you will need the following credentials: - SINCH_ENGAGE_API_KEY and SINCH_ENGAGE_API_SECRET Sinch Engage Credentials
6 tools · Generate a detailed message report, Generate a summary message report