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.
-
Use Deepgram with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
A Model Context Protocol (MCP) server that integrates Twilio Voice, Deepgram AI, and OpenAI to create intelligent voice-based HR automation tools.
★ 3 -
Open-source AI phone API for voice agents. Give Claude, Cursor, OpenClaw, or any LLM a real phone number — outbound/inbound calls, SMS, transcripts, MCP, DTMF/IVR. FastAPI + SignalWire + Deepgram. Self-hostable alternative to Twilio, Vapi, and Retell.
MIT ★ 62 -
Windows desktop app for cloud audio transcription and speaker diarization (AssemblyAI / Deepgram / Gladia / Speechmatics) with KZ+RU+EN code-switching, LLM task extraction to Linear / Trello / Glide, and meeting protocol generation
MIT ★ 1 -
meetscribegithub.com/qa-aman/meetscribeupdated this year
Record, transcribe, and extract action items from meetings inside Claude Code. Bring your own API key. macOS, Node 18+.
MIT ★ 3 -
isipgithub.com/nwalker85/isipupdated this year
Give an AI agent a phone — an MCP server (+ Python SDK & CLI) that lets AI agents place real phone calls over SIP. Built on PJSIP.
MIT -
patter-mcpgithub.com/PatterAI/patter-mcpupdated this year
MCP server for the Patter Voice AI SDK — make and receive phone calls from any MCP-compatible client (Claude Code, Cursor, ChatGPT, OpenClaw, Hermes Agent, Codex). Streamable HTTP transport, self-hosted via git clone + npm start.
MIT ★ 4 -
Benchmark the full voice-AI pipeline on your own audio — STT (batch + streaming), LLM TTFT, speech-to-speech, and TTS. WER by failure mode, keyterm recall, real-time-paced latency, cost columns, a CI regression gate, and an MCP server for coding agents.
MIT ★ 1