feat(integrations): SP-4 multi-platform MCP — codetalker-mcp alias + per-agent docs#3
Merged
Conversation
Adds the multi-platform reach for codetalker per SP-4 of the commercial
launch master plan. CodeTalker already ships an MCP server
(claude-code-talker-mcp-stdio) that any MCP-compatible AI agent can
connect to — the work this PR adds is packaging + discoverability:
1. **Shorter console_script alias** in core/pyproject.toml:
- codetalker-mcp = claude_code_talker.mcp_stdio:main
- Existing claude-code-talker-mcp-stdio kept for backwards compat.
2. **Per-agent integration docs** in docs/integrations/ covering:
- Claude Code (canonical), Cursor, Cline (VS Code), Continue.dev,
Windsurf, Zed, Codex CLI, Goose, Roo Code, Replit Agent,
AWS Kiro, Google Antigravity
- Plus v1.x stubs for Aider (bespoke CLI wrapper) and JetBrains AI
Assistant (bespoke plugin) — these are Pro Plus targets per the
master plan, scheduled post-launch.
3. **MCP registry submission metadata** in docs/integrations/mcp-registries.md
— canonical YAML + submission status for the 8 MCP registries:
- registry.modelcontextprotocol.io (official, Sept 2025)
- PulseMCP, MCP.so, mcpservers.org
- GitHub MCP Registry, modelcontextprotocol/servers awesome-list
- Anthropic Claude Marketplace, Continue Hub
4. **README update** with a 'Use with other AI-coding agents' section
linking to the new integration guides.
No daemon-side code changes — the existing 9 agent-facing MCP tools
(tts_speak, tts_set_mode, tts_status, tts_mute, tts_unmute,
tts_list_voices, tts_set_voice, tts_set_cadence, tts_shutdown) already
work with any MCP client.
Session-scoped tool variants (narrate with voice/mode args,
session_set_mode, session_set_mute, session_list) ship in a follow-up
PR per the master plan's split-PR strategy.
Refs: docs/superpowers/specs/2026-05-09-cct-30-open-core-strategy.md
Refs: C:/Users/brand/.claude/plans/i-want-to-start-merry-treasure.md
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Implements SP-4 of the commercial launch master plan: expand codetalker from "Claude Code TTS" to "TTS for any MCP-compatible AI coding agent" via packaging + discoverability changes (no daemon code touched).
The existing MCP server (
claude-code-talker-mcp-stdio) already works with any MCP client; this PR makes that fact findable and frictionless for users of the other agents in the AI-coding ecosystem.What's in this PR
1.
codetalker-mcpconsole_script aliascore/pyproject.tomladdscodetalker-mcp = "claude_code_talker.mcp_stdio:main"claude-code-talker-mcp-stdiostays for backwards compat2. Per-agent integration guides —
docs/integrations/Twelve installable platforms documented with copy-paste config snippets:
3. MCP registry submission metadata —
docs/integrations/mcp-registries.mdCanonical YAML metadata + submission status for the 8 MCP registries codetalker will be listed in at v1 launch (registry.modelcontextprotocol.io, PulseMCP, MCP.so, mcpservers.org, GitHub MCP Registry, awesome-list, Anthropic Claude Marketplace, Continue Hub).
4. README.md — "Use with other AI-coding agents" section
Top-level discoverability for the new docs.
What's NOT in this PR (intentionally split out)
narratewith voice/mode args,session_set_mode,session_set_mute,session_list) — these touchserver.py'sregister_tools()and the shim's_PROXY_TOOLS. Bigger, riskier change; ships as a follow-up PR.attach_character,list_characters) — those tools don't exist yet; they ship as part of SP-2 (character system cleave to private repo) + SP-3 (entitlement server).Test plan
cd core && pip install -e .succeeds and exposes bothclaude-code-talker-mcp-stdioandcodetalker-mcpon PATHcodetalker-mcp --version(or invocation via an MCP client) launches the same shim as the verbose namedocs/integrations/*.mdfile in a Markdown viewer — verify code blocks lex correctly and table formatting is intacttts_statusround-tripsThe first three are quick verification; the fourth is the real smoke test and can land in a follow-up if a tester isn't immediately available.
🤖 Generated with Claude Code