ClawCall MCP Server
Enables AI agents to make real outbound phone calls to US/Canada numbers, handle conversations, and return transcripts and recordings via the Model Context Protocol.
README
ClawCall
Make real AI-powered phone calls from any AI agent. ClawCall dials the number, has the conversation, and brings back a full transcript.
10 free minutes or 10 calls. No setup. No API keys to configure.
Install From ClawHub
openclaw skills install clawcall-dev
Published skill: https://clawhub.ai/clawcall-dev/clawcall-dev
Or manually, download the skill zip from ClawHub and add SKILL.md to your agent's skills directory.
MCP Server
Prefer the Model Context Protocol? mcp/ is a stdio MCP server that exposes the
same ClawCall REST API as tools for any MCP host (Claude Code, Claude Desktop, Cursor,
Windsurf). It shares one identity and balance with the skill.
claude mcp add clawcall -- npx -y @clawcall/mcp
See mcp/README.md for client config and the call workflow. The skill is
the procedural layer; the MCP server is the connectivity layer — both wrap the public API at
https://api.clawcall.dev.
What users learn on install
When the skill is installed or first introduced, the agent should explain:
- ClawCall makes real outbound phone calls in the US and Canada
- The AI can handle appointments, reservations, order checks, callbacks, office follow-ups, voicemail/messages, phone menus, and hold queues
- The user can be patched in live when a call needs identity verification, negotiation, or a real-time decision
- Users can configure reusable voice, personality, greeting, and inbound reserved-number answering preferences
- Completed calls return the outcome first, with transcript details and a temporary recording URL available
- The first call auto-creates a low-privilege API key, and new users get 10 free minutes or 10 calls, whichever comes first
What it does
- Calls US and Canada phone numbers over real phone lines
- AI agent handles the full conversation based on your task briefing
- Leaves voicemail or takes messages when the task asks for it
- Returns a complete transcript and recording
- Live handoff: the AI navigates phone trees and hold queues, then connects you in to speak directly
- Reusable voice/personality profile setup for outbound and inbound answering
- Automatic retry and callback when a call needs more information
Examples
"Call Dr. Rivera's office and confirm my appointment for Tuesday at 2:30"
"Phone the restaurant at +15551234567 and make a reservation for 4 people Saturday at 7 PM"
"Get me through to a real person at my insurance company - here's the number"
Links
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.