Magpipe

by elagerway

Not rated
GitHub

About

Open-source omni-channel agentic communications platform

Details

Author
elagerway
Categories
Communication, Automation, AI

Setup

Install Magpipe in your MCP client (Claude Desktop, Cursor, Windsurf, and others).

Repository: https://github.com/elagerway/magpipe

Follow the installation instructions in the repository README, then restart your MCP client.

MCP server forMagpipe— manage agents, calls, SMS, contacts, and phone numbers from AI coding tools like Claude Code and Cursor.

Go tomagpipe.ai/settings→APItab →Generate New Key.

{ "mcpServers": { "magpipe": { "command": "npx", "args": ["-y", "magpipe-mcp-server"], "env": { "MAGPIPE_API_KEY": "mgp_your_key_here" } } } }
{ "mcpServers": { "magpipe": { "command": "npx", "args": ["-y", "magpipe-mcp-server"], "env": { "MAGPIPE_API_KEY": "mgp_your_key_here" } } } }

- list_agents— List all agents with optional filters
- get_agent— Get full agent details including assigned phone numbers, custom functions, knowledge sources, and dynamic variables
- create_agent— Create a new agent
- update_agent— Update agent configuration
- delete_agent— Delete an agent

- list_calls— List call records with filters
- get_call— Get call details, transcript, and summary
- initiate_call— Place an outbound call
- terminate_call— End an active call
- get_recording— Get a signed recording URL

- list_messages— List SMS messages
- get_message— Get a single message
- send_sms— Send an SMS

- list_phone_numbers— List provisioned numbers
- search_phone_numbers— Search available numbers to purchase
- provision_phone_number— Purchase a number
- release_phone_number— Release a number

- list_contacts— List contacts with search and filters
- get_contact— Get contact details
- create_contact— Create a contact
- update_contact— Update a contact
- delete_contact— Delete a contact

- list_knowledge_sources— List knowledge sources for an agent
- add_knowledge_source— Add URL-based knowledge
- add_knowledge_manual— Add manual text knowledge
- delete_knowledge_source— Delete a knowledge source
- sync_knowledge_source— Re-crawl a URL source

- list_voices— List available voices
- delete_voice— Delete a cloned voice

- get_calendar_slots— Get available booking slots
- create_booking— Create a booking
- cancel_booking— Cancel a booking

- manage_api_keys— Generate, list, revoke, or update API keys

- list_models— List available LLM models
- chat_with_agent— Send a text message to an agent
- list_chat_sessions— List chat sessions
- list_custom_functions— List custom functions
- create_custom_function— Create a custom function
- manage_dynamic_variables— Manage data extraction variables
- list_scheduled_actions— List scheduled actions

cd packages/mcp-server npm install npm run build MAGPIPE_API_KEY=mgp_xxx node dist/index.js

An MCP server client for the Agent-to-Agent (A2A) protocol, enabling LLMs to interact with A2A agents.

A bridge server connecting Model Context Protocol (MCP) with Agent-to-Agent (A2A) protocol.

A bridge server connecting Model Context Protocol (MCP) with Agent-to-Agent (A2A) protocol.

Production-grade multi-agent communication MCP server with 58 tools over MCP+SSE — real-time messaging, task scheduling, shared memory, and a trust-based evolution engine. SQLite WAL persistence, 4-level RBAC, zero-dependency Python/TypeScript SDKs.

Enables room-based messaging between multiple agents.

Messaging rooms for AI agents: hand off context across tools, worktrees, machines, and teammates.

Agent-to-agent messaging platform. any MCP-compatible agent sends and receives direct messages

Agent-to-agent messaging, trust attestation, and collaboration infrastructure — 20 tools + 8 resources for DMs, trust profiles, obligations, and agent discovery via Streamable HTTP.

Enables AI assistants to request human input through a web interface, facilitating human-in-the-loop interactions.

Agent-native collaboration network: orchestrate a team of long-running agents from any MCP client, with persistent identity, real-time messaging with @mentions and threads, task handoffs, shared workspace context, semantic search, and replayable MCP App widgets.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.