{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_4hcjxe3n6n4w","handle":"pipecat-ai-mcp-server","url":"https://wellknown.network/agents/pipecat-ai-mcp-server","links":{"self":"https://wellknown.network/agents/pipecat-ai-mcp-server/record.json","html":"https://wellknown.network/agents/pipecat-ai-mcp-server","markdown":"https://wellknown.network/agents/pipecat-ai-mcp-server/record.md","api":"https://wellknown.network/api/v1/agents/pipecat-ai-mcp-server","status":"https://wellknown.network/api/v1/agents/pipecat-ai-mcp-server/status","claim":"https://wellknown.network/agents/pipecat-ai-mcp-server/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/pipecat-ai-mcp-server/claim.json","badge":"https://wellknown.network/agents/pipecat-ai-mcp-server/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/pipecat-ai-mcp-server/history","tools":"https://wellknown.network/api/v1/agents/pipecat-ai-mcp-server/tools"},"ard":{"identifier":"urn:air::server:pipecat-ai-mcp-server","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"pipecat-ai-mcp-server","summary":"Pipecat MCP server for your AI agents","description":"

\n \"Pipecat\n

\n\n[![PyPI](https://img.shields.io/pypi/v/pipecat-ai-mcp-server)](https://pypi.org/project/pipecat-ai-mcp-server) [![Discord](https://img.shields.io/discord/1239284677165056021)](https://discord.gg/pipecat)\n\n# Pipecat MCP Server\n\nPipecat MCP Server gives your AI agents a voice using [Pipecat](https://github.com/pipecat-ai/pipecat). It should work with any [MCP](https://modelcontextprotocol.io/)-compatible client:\n\nThe Pipecat MCP Server exposes **voice-related** and **screen capture** tools to MCP-compatible clients, but **it does not itself provide microphone or speaker access**.\n\nAudio input/output is handled by a **separate audio/video transport**, such as:\n\n- **Pipecat Playground** (local browser UI)\n- **Daily** (WebRTC room)\n- **Phone providers** (Twilio, Telnyx, etc.)\n\n> **MCP clients like Cursor, Claude Code, and Codex control the agent, but they are not audio devices.**\n> To hear, speak or see, you must connect via one of the audio transports.\n\n

\n\n## 🧭 Getting started\n\n### Prerequisites\n\n- Python 3.10 or later\n- [uv](https://docs.astral.sh/uv/getting-started/installation/) package manager\n\nBy default, the voice agent uses local models (no API keys required): [Faster Whisper](https://github.com/SYSTRAN/faster-whisper) for speech-to-text and [Kokoro](https://github.com/hexgrad/kokoro) for text-to-speech. The Whisper models are approximately 1.5 GB and are downloaded automatically on the first connection, so the initial startup may take a moment.\n\n### Installation\n\n```bash\nuv tool install pipecat-ai-mcp-server\n```\n\nThis will install the `pipecat-mcp-server` tool.\n\nIf you want to use different services or modify the Pipecat pipeline somehow,…","publisher":null,"homepage":"https://docs.pipecat.ai/","repository":"https://github.com/pipecat-ai/pipecat-mcp-server/blob/main/CHANGELOG.md","version":"0.0.12","license":null,"protocols":["mcp"],"tags":["pipecat","mcp","voice","ai","assistant","speech"],"pricing":null,"endpoints":[{"url":"pypi:pipecat-ai-mcp-server","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"media.speech-recognition","name":"Speech Recognition","confidence":0.859,"provenance":"derived"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.768,"provenance":"derived"},{"slug":"communication.sms-voice","name":"SMS & Voice","confidence":0.768,"provenance":"derived"}],"categories":["communication","dev","media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"pipecat-ai-mcp-server","registry":"pypi","observedAt":"2026-10-28T19:22:56.101Z","publishedAt":"2026-02-11T04:18:43.063365Z","latestVersion":"0.0.12"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"pipecat-ai-mcp-server","url":"https://pypi.org/project/pipecat-ai-mcp-server/","firstSeenAt":"2026-09-10T09:26:26.725Z","fetchedAt":"2026-10-28T19:22:17.823Z","normalizedAt":"2026-10-28T19:22:17.823Z"}]},"firstSeenAt":"2026-09-10T09:26:26.725Z","updatedAt":"2026-10-28T19:22:56.101Z"}