Skip to content
Back to search

pipecat-mcp-server

Pipecat MCP server for your AI agents

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/pipecat-ai--pipecat-mcp-server/badge.svg)](/listings/pipecat-ai--pipecat-mcp-server)

HTML

<a href="/listings/pipecat-ai--pipecat-mcp-server"><img src="/api/listings/pipecat-ai--pipecat-mcp-server/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Prerequisites

- Python 3.10 or later - [uv](https://docs.astral.sh/uv/getting-started/installation/) package manager

By 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.

Installation

uv tool install pipecat-ai-mcp-server

This will install the `pipecat-mcp-server` tool.

If you want to use different services or modify the Pipecat pipeline somehow, you will need to clone the repository:

git clone https://github.com/pipecat-ai/pipecat-mcp-server.git

and install your local version with:

uv tool install -e /path/to/repo/pipecat-mcp-server

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 264 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <h1><div align="center">
  2. <img alt="Pipecat MCP Server" width="300px" height="auto" src="https://github.com/pipecat-ai/pipecat-mcp-server/raw/refs/heads/main/pipecat.png">
  3. </div></h1>
  4. [![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)
  5. # Pipecat MCP Server
  6. Pipecat 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:
  7. The Pipecat MCP Server exposes **voice-related** and **screen capture** tools to MCP-compatible clients, but **it does not itself provide microphone or speaker access**.
  8. Audio input/output is handled by a **separate audio/video transport**, such as:
  9. - **Pipecat Playground** (local browser UI)
  10. - **Daily** (WebRTC room)
  11. - **Phone providers** (Twilio, Telnyx, etc.)
  12. > **MCP clients like Cursor, Claude Code, and Codex control the agent, but they are not audio devices.**
  13. > To hear, speak or see, you must connect via one of the audio transports.
  14. <p align="center"><video src="https://github.com/user-attachments/assets/0ad14e37-2de7-46df-870a-167aa667df16" width="500" controls></video></p>
  15. ## 🧭 Getting started
  16. ### Prerequisites
  17. - Python 3.10 or later
  18. - [uv](https://docs.astral.sh/uv/getting-started/installation/) package manager
  19. By 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.
  20. ### Installation
  21. ```bash
  22. uv tool install pipecat-ai-mcp-server
  23. ```
  24. This will install the `pipecat-mcp-server` tool.
  25. If you want to use different services or modify the Pipecat pipeline somehow, you will need to clone the repository:
  26. ```bash
  27. git clone https://github.com/pipecat-ai/pipecat-mcp-server.git
  28. ```
  29. and install your local version with:
  30. ```bash
  31. uv tool install -e /path/to/repo/pipecat-mcp-server
  32. ```
  33. ## Running the server
  34. Start the server:
  35. ```bash
  36. pipecat-mcp-server
  37. ```
  38. This will make the Pipecat MCP Server available at `http://localhost:9090/mcp`.
  39. ## Auto-approving permissions
  40. For hands-free voice conversations, you will need to auto-approve tool permissions. Otherwise, your agent will prompt for confirmation, which interrupts the conversation flow.
  41. > ⚠️ **Warning**: Enabling broad permissions is at your own risk.
  42. ## Installing the talk skill (recommended)
  43. The [talk skill](https://github.com/pipecat-ai/skills/blob/main/skills/talk/SKILL.md) provides a better voice conversation experience. It asks for verbal confirmation before making changes to files, adding a layer of safety when using broad permissions.
  44. If you're using Claude Code, install the marketplace and plugin:
  45. ```
  46. /plugin marketplace add pipecat-ai/skills
  47. /plugin install pipecat-mcp-server@pipecat-skills
  48. ```
  49. Alternatively, just tell your agent something like `Let's have a voice conversation`. In this case, the agent won't ask for verbal confirmation before making changes.
  50. ## 🖥️ Screen Capture & Analysis
  51. Screen capture lets you stream your screen (or a specific window) to your configured transport, and ask the agent to help with what it sees.
  52. For example:
  53. - *"capture my browser window"* — starts streaming that window
  54. - *"what's causing this error?"* — the agent analyzes the screen and helps debug
  55. - *"how does this UI look?"* — get feedback on your design
  56. **Supported platforms:**
  57. - **macOS** — uses ScreenCaptureKit for true window-level capture (not affected by overlapping windows)
  58. - **Linux (X11)** — uses Xlib for window and full-screen capture
  59. ## 💻 MCP Client: Claude Code
  60. ### Adding the MCP server
  61. Register the MCP server:
  62. ```bash
  63. claude mcp add pipecat --transport http http://localhost:9090/mcp --scope user
  64. ```
  65. Scope options:
  66. - `local`: Stored in `~/.claude.json`, applies only to your project
  67. - `user`: Stored in `~/.claude.json`, applies to all projects
  68. - `project`: Stored in `.mcp.json` in your project directory
  69. ### Auto-approving permissions
  70. Create `.claude/settings.local.json` in your project directory:
  71. ```json
  72. {
  73. "permissions": {
  74. "allow": [
  75. "Bash",
  76. "Read",
  77. "Edit",
  78. "Write",
  79. "WebFetch",
  80. "WebSearch",
  81. "mcp__pipecat__*"
  82. ]
  83. }
  84. }
  85. ```
  86. This grants permissions for bash commands, file operations, web fetching and searching, and all Pipecat MCP tools without prompting. See [available tools](https://code.claude.com/docs/en/settings#tools-available-to-claude) if you need to grant more permissions.
  87. ### Starting a voice conversation
  88. 1. Install the talk skill (see above).
  89. 2. Start the Pipecat MCP Server.
  90. 3. Connect to an audio transport (see **🗣️ Connecting to the voice agent** below).
  91. 4. Run `/talk`.
  92. ## 💻 MCP Client: Cursor
  93. ### Adding the MCP server
  94. Register the MCP server by editing `~/.cursor/mcp.json`:
  95. ```json
  96. {
  97. "mcpServers": {
  98. "pipecat": {
  99. "url": "http://localhost:9090/mcp"
  100. }
  101. }
  102. }
  103. ```
  104. ### Auto-approving permissions
  105. Go to the `Auto-Run` agent settings and configure it to `Run Everything`.
  106. ### Starting a voice conversation
  107. 1. Install the talk skill into `.claude/skills/talk/SKILL.md` (Cursor supports the Claude skills location).
  108. 2. Start the Pipecat MCP Server.
  109. 3. Connect to an audio transport (see **🗣️ Connecting to the voice agent** below).
  110. 4. In a **new Cursor agent**, run `/talk`.
  111. ## 💻 MCP Client: OpenAI Codex
  112. ### Adding the MCP server
  113. Register the MCP server:
  114. ```bash
  115. codex mcp add pipecat --url http://localhost:9090/mcp
  116. ```
  117. ### Auto-approving permissions
  118. If you start `codex` inside a version controlled project, you will be asked if you allow Codex to work on the folder without approval. Say `Yes`, which adds the following to `~/.codex/config.toml`.
  119. ```toml
  120. [projects."/path/to/your/project"]
  121. trust_level = "trusted"
  122. ```
  123. ### Starting a voice conversation
  124. 1. Install the talk skill into `.codex/skills/talk/SKILL.md`.
  125. 2. Start the Pipecat MCP Server.
  126. 3. Connect to an audio transport (see **🗣️ Connecting to the voice agent** below).
  127. 4. Run `$talk`.
  128. ## 🗣️ Connecting to the voice agent
  129. Once the voice agent starts, you can connect using different methods depending on how the server is configured.
  130. ### Pipecat Playground (default)
  131. When no arguments are specified to the `pipecat-mcp-server` command, the server uses Pipecat's local playground. Connect by opening http://localhost:7860 in your browser.
  132. You can also run an ngrok tunnel that you can connect to remotely:
  133. ```
  134. ngrok http --url=your-proxy.ngrok.app 7860
  135. ```
  136. ### Daily Prebuilt
  137. You can also use [Daily](https://daily.co) and access your agent through a Daily room, which is convenient because you can then access from anywhere without tunnels.
  138. First, install the server with the Daily dependency:
  139. ```bash
  140. uv tool install pipecat-ai-mcp-server[daily]
  141. ```
  142. Then, set the `DAILY_API_KEY` environment variable to your Daily API key and `DAILY_ROOM_URL` to your desired Daily room URL and pass the `-d` argument to `pipecat-mcp-server`.
  143. ```bash
  144. export DAILY_API_KEY=your-daily-api-key
  145. export DAILY_ROOM_URL=your-daily-room
  146. pipecat-mcp-server -d
  147. ```
  148. Connect by opening your Daily room URL (e.g., `https://yourdomain.daily.co/room`) in your browser. Daily Prebuilt provides a ready-to-use video/audio interface.
  149. ### Phone call
  150. To connect via phone call, pass `-t <provider> -x <your-proxy>` where `<provider>` is one of `twilio`, `telnyx`, `exotel`, or `plivo`, and `<your-proxy>` is your ngrok tunnel domain (e.g., `your-proxy.ngrok.app`).
  151. First, start your ngrok tunnel:
  152. ```bash
  153. ngrok http --url=your-proxy.ngrok.app 7860
  154. ```
  155. Then, run the Pipecat MCP server with your ngrok URL and the required environment variables for your chosen telephony provider.
  156. | Provider | Environment variables |
  157. |----------|-------------------------------------------|
  158. | Twilio | `TWILIO_ACCOUNT_SID`, `TWILIO_AUTH_TOKEN` |
  159. | Telnyx | `TELNYX_API_KEY` |
  160. | Exotel | `EXOTEL_API_KEY`, `EXOTEL_API_TOKEN` |
  161. | Plivo | `PLIVO_AUTH_ID`, `PLIVO_AUTH_TOKEN` |
  162. #### Twilio
  163. ```bash
  164. export TWILIO_ACCOUNT_SID=your-twilio-account-sid
  165. export TWILIO_AUTH_TOKEN=your-twilio-auth-token
  166. pipecat-mcp-server -t twilio -x your-proxy.ngrok.app
  167. ```
  168. Configure your provider's phone number to point to your ngrok URL, then call your number to connect.
  169. ## 📚 What's Next?
  170. - **Customize services**: Edit `agent.py` to use different STT/TTS providers
  171. - **Change transport**: Configure for Twilio, WebRTC, or other transports
  172. - **Add to your project**: Use this as a template for voice-enabled MCP tools
  173. - **Learn more**: Check out [Pipecat's docs](https://docs.pipecat.ai/) for advanced features
  174. - **Get help**: Join [Pipecat's Discord](https://discord.gg/pipecat) to connect with the community

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.