Skip to content

Releases: pipecat-ai/pipecat-mcp-server

v0.0.12

11 Feb 04:18

Choose a tag to compare

Fixed

  • Fixed an issue where multiprocessing queues were not properly closed during cleanup, which could cause resource leaks.

  • Increased process join timeout from 1s to 5s for more reliable shutdown.

v0.0.11

03 Feb 06:40
33e9efd

Choose a tag to compare

Added

  • New capture_screenshot() MCP tool that captures the current screen frame and returns an image path. This allows the agent to visually analyze what's on screen and help with debugging, UI feedback, and more.

v0.0.10

01 Feb 23:18

Choose a tag to compare

Added

  • New list_windows() MCP tool to list all open windows with title, app name, and window ID.

  • New screen_capture(window_id) MCP tool to start or switch screen capture to a specific window or full screen during a voice conversation.

Changed

  • Screen capture dependencies are now included by default (no longer an optional [screen] extra).

  • Screen capture is no longer configured via environment variables (PIPECAT_MCP_SERVER_SCREEN_CAPTURE, PIPECAT_MCP_SERVER_SCREEN_WINDOW). Use the list_windows() and screen_capture() tools instead.

v0.0.9

01 Feb 07:40

Choose a tag to compare

Changed

  • Linux X11 screen capture backend using python-xlib.

  • Native macOS screen capture using ScreenCaptureKit. Supports true window-level capture not affected by overlapping windows.

v0.0.8

01 Feb 01:46

Choose a tag to compare

Changed

  • Updated to Pipecat >= 0.0.101.

v0.0.7

01 Feb 00:53

Choose a tag to compare

Changed

  • KokoroTTSService now uses kokoro-onnx.

v0.0.6

30 Jan 03:02
f5e820c

Choose a tag to compare

Added

  • Added KokoroTTSService processor.

  • Added noise cancellation with RNNoiseFilter.

  • Simplified the /pipecat skill instructions.

Changed

  • Replaced third-party STT/TTS services (Deepgram, Cartesia) with local models: Faster Whisper for speech-to-text and Kokoro for text-to-speech. No API keys required.

v0.0.5

28 Jan 18:37

Choose a tag to compare

Fixed

  • Fixed an issue that would cause an MCP session to crash and would force the MCP client to reconnect each time.

v0.0.4

27 Jan 01:25

Choose a tag to compare

Fixed

  • Fixed an issue where Daily clients couldn't reconnect after disconnecting.

v0.0.3

27 Jan 01:00

Choose a tag to compare

Fixed

  • Fixed premature exit of the /pipecat skill when user responds with phrases like "no", "nothing", or "that's it" instead of explicit ending phrases.

  • Fixed an issue where WebRTC clients couldn't reconnect after disconnecting. The agent now properly handles disconnect/reconnect cycles.

  • Fixed an issue where pipecat-mcp-server could hang indefinitely after pressing Ctrl-C.