What are the prerequisites to run this server?
Node.js v22+, a Twilio account with an outbound phone number, a Deepgram API key, and a publicly accessible URL (e.g., ngrok) for webhooks.
@prakharbhardwaj
Basic information
A Model Context Protocol (MCP) server that integrates Twilio Voice, Deepgram AI, and OpenAI to create intelligent voice-based HR automation tools.
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
A Model Context Protocol (MCP) server that integrates Twilio Voice, Deepgram AI, and OpenAI to create intelligent voice-based HR automation tools. It enables AI assistants like Claude to conduct phone interviews, deliver notifications, and manage HR communications through natural voice conversations.
Install with Node.js v22+, set up environment variables for Twilio, Deepgram, and a public URL. Run npm run dev to start the server. Configure Claude Desktop by adding the MCP server to the Claude Desktop configuration file using the absolute path to the Node.js binary and project directory.
Node.js v22+, a Twilio account with an outbound phone number, a Deepgram API key, and a publicly accessible URL (e.g., ngrok) for webhooks.
Add the MCP server configuration to `claude_desktop_config.json` with the absolute path to Node.js and your project’s `mcp-server.js`, plus all required environment variables.
Five tools: `conduct_interview`, `notify_interview_result`, `discuss_job_opening`, `get_call_status`, and `check_twilio_config`. Each accepts specific parameters like candidate phone number and name, and can be invoked via natural language in Claude.
Ensure your server URL is publicly accessible, verify Twilio webhooks are correctly configured, check environment variables are set, and that MCP config paths are absolute. Detailed logs are available in `src/mcp/mcp-server.log`.
Yes, if you encounter a `SyntaxError: Unexpected identifier`, it is often because Claude Desktop cannot find the correct Node.js binary. Use the absolute path to your Node.js binary (found with `which node`) in the MCP configuration.
HeyLead: AI agent for LinkedIn outreach. Finds the right people, writes in your voice, follows up and handles replies, from Claude Code, Cursor, any MCP client or a web dashboard.
NetFoundry MCP Gateway enables secure, isolated access to Model Context Protocol (MCP) tools across distributed systems without exposing public endpoints. Zero trust gateway for MCP servers. Aggregate, filter, and secure
Open-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.

Operate a real LinkedIn account from your AI agent. 52 tools for the inbox, invitations, network, profiles, Sales Navigator search in plain language, posts and engagement; six playbooks served as MCP prompts that preview
Sphere is an exchange where AI agents list services and post requests for other agents. Registration is one request, free, with no human approval. The first order is free: sphere_receipt_trial, one per agent per 24 hours
Comments