Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion servers/voice/pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ version = "0.0.1"
description = "WorldOS voice MCP: swappable text-to-speech (Kokoro local default; ElevenLabs optional)."
requires-python = ">=3.11,<3.13"
dependencies = [
"mcp>=1.28.1",
"mcp>=2.0.0",

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Port voice server before requiring MCP v2

With this requirement, fresh uv run --directory servers/voice server.py installs MCP 2.x, but the voice MCP server still imports from mcp.server.fastmcp import FastMCP and instantiates FastMCP in servers/voice/server.py; upstream v2 docs say that old import path is gone and the class is now MCPServer, so the configured worldos-voice stdio server exits at import time before registering ping, speak, or transcribe. Please either port server.py to the v2 API or keep an upper bound such as <2 until the port lands.

Useful? React with 👍 / 👎.

]

[dependency-groups]
Expand Down
139 changes: 85 additions & 54 deletions servers/voice/uv.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

Loading