A
licenseNot graded
qualityB
maintenanceEnables voice-driven control of coding agents via Claude on your phone, allowing status checks, stand-ups, sending prompts, and receiving push notifications when agents finish or need decisions.
MIT
t3-code-mcp
Related Servers
Alternatives to t3-code-mcp
No user-submitted related servers found.
Related Servers
- AlicenseAqualityDmaintenanceManage voice AI agents from Claude Code, Cursor, VS Code, or any MCP-compatible assistant.39 npm3MIT
- AlicenseNot gradedqualityCmaintenanceEnables coding agents to receive and act on voice-captured tasks delivered as GitHub issues, including retrieving full context, adding notes, asking the developer questions, and closing tasks when complete.MIT
- AlicenseNot gradedqualityBmaintenanceEnables voice-first interactions with AI agents and MCP tools, supporting speech input/output, STT/TTS, and a provider-independent agent core.1MIT
t3threads MCP Serverofficial
AlicenseNot gradedqualityAmaintenanceEnables reading, searching, and starting T3 Code conversations through typed tools, with agent-launching and read operations distinguished.2,298 npmMIT- FlicenseNot gradedqualityBmaintenanceEnables voice control of local Claude Code sessions running in tmux, allowing users to list, read, send messages to, and manage sessions via nine MCP tools.-
TDQS
A3.7/5.0
Scored across 15 tools
Disambiguation4/5
Most tools target a distinct resource and action, and the t3_run_* and t3_thread_* groups are largely well separated. The closest ambiguities are t3_run_interrupt vs t3_thread_interrupt and t3_thread_get vs t3_thread_messages, but the descriptions establish clear boundaries.
Naming Consistency4/5
All tools share the t3_ prefix and snake_case, with a mostly predictable resource_action pattern. Minor inconsistencies exist: plural forms like projects_list and pending_actions_list mix with singular forms, and connection_status and thread_messages are noun-like names rather than clear verb-first operations.
Tool Count4/5
At 15 tools, the surface is at the high end but still justifiable given projects, threads, runs, pending actions, and connection inspection each have separate workflows. A few operations could arguably be consolidated, but the set is not bloated enough to be a real usability problem.
Completeness4/5
The main workflow is covered end-to-end: project creation, thread creation and messaging, run waiting and interruption, and pending-action response are all present. Gaps remain around explicit project/thread updates or deletion, though thread archive and thread send act as partial lifecycle operations.
Maintenance
ActivityMaintained
ResponsivenessUnresponsive