docs: refer to the MCP tools by their new underscore names

Update the README, MCP docs, in-app MCP page, i18n strings, landing copy,
docstrings and comments to match the renamed tools. CHANGELOG entries and
docs/plans are historical and left as they were.

backend/database/migrations.py

@@ -250,7 +250,7 @@ def _migrate_mcp_bindings(engine, inspector, tables: set[str]) -> None:
     """Drop the legacy ``default_intent`` column and add ``default_personality``.
 
     The intent tri-state (respond / rewrite / compose) has been collapsed
-    to a boolean: when true, ``voicebox.speak`` rewrites input through the
+    to a boolean: when true, ``voicebox_speak`` rewrites input through the
     profile's personality LLM before TTS.
     """
     if "mcp_client_bindings" not in tables:

backend/database/models.py

@@ -272,7 +272,7 @@ class MCPClientBinding(Base):
     label = Column(String, nullable=True)  # display name
     profile_id = Column(String, ForeignKey("profiles.id"), nullable=True)
     default_engine = Column(String, nullable=True)
-    # When true, voicebox.speak routes through the profile's personality LLM
+    # When true, voicebox_speak routes through the profile's personality LLM
     # (rewrite) before TTS by default. Callers can still override per call.
     default_personality = Column(Boolean, nullable=False, default=False)
     last_seen_at = Column(DateTime, nullable=True)

backend/mcp_server/README.md

@@ -49,10 +49,10 @@ claude mcp add voicebox \
 
 | Name | Purpose |
 |---|---|
-| `voicebox.speak`          | Speak text in a voice profile. Returns a generation id you can poll. |
-| `voicebox.transcribe`     | Whisper transcription of a base64 blob or an absolute local path. |
-| `voicebox.list_captures`  | Recent captures (dictation / recording / file) with transcripts. |
-| `voicebox.list_profiles`  | Available voice profiles (cloned + preset). |
+| `voicebox_speak`          | Speak text in a voice profile. Returns a generation id you can poll. |
+| `voicebox_transcribe`     | Whisper transcription of a base64 blob or an absolute local path. |
+| `voicebox_list_captures`  | Recent captures (dictation / recording / file) with transcripts. |
+| `voicebox_list_profiles`  | Available voice profiles (cloned + preset). |
 
 All tools resolve voice profiles in this precedence:
 
@@ -69,8 +69,8 @@ Settings → MCP.
 npx @modelcontextprotocol/inspector http://127.0.0.1:17493/mcp
 ```
 
-Point it at the URL, hit "List tools," call `voicebox.list_profiles`
-first to confirm wiring, then `voicebox.speak` for end-to-end.
+Point it at the URL, hit "List tools," call `voicebox_list_profiles`
+first to confirm wiring, then `voicebox_speak` for end-to-end.
 
 ## Non-MCP REST surface
 

backend/mcp_server/context.py

@@ -33,7 +33,7 @@ current_client_id: ContextVar[str | None] = ContextVar(
 )
 
 # Remote address of the in-flight request. Used by tools that gate
-# host-filesystem access to loopback callers (see voicebox.transcribe).
+# host-filesystem access to loopback callers (see voicebox_transcribe).
 current_remote_addr: ContextVar[str | None] = ContextVar(
     "current_remote_addr", default=None
 )
@@ -61,12 +61,12 @@ def request_is_loopback() -> bool:
 # ignored so the Settings UI's "last heard from" column only reflects
 # calls that actually acted on the client's bindings.
 #
-# - /mcp — FastMCP tool calls (voicebox.speak, voicebox.transcribe, …)
+# - /mcp — FastMCP tool calls (voicebox_speak, voicebox_transcribe, …)
 #   and the /mcp/bindings admin surface. The admin surface is never
 #   called with the header in practice (the frontend manages bindings
 #   over plain REST), so the `startswith("/mcp")` match doesn't cause
 #   false stamps.
-# - /speak — REST mirror of voicebox.speak for non-MCP agents (shell
+# - /speak — REST mirror of voicebox_speak for non-MCP agents (shell
 #   scripts, ACP, A2A). Uses the same per-client binding lookup, so its
 #   callers belong in the last-seen list too.
 _STAMPED_PATH_PREFIXES: tuple[str, ...] = ("/mcp", "/speak")

backend/mcp_server/events.py

@@ -1,6 +1,6 @@
 """In-memory pub/sub for speaking-pill SSE broadcasts.
 
-MCP ``voicebox.speak`` calls and the REST ``POST /speak`` route publish
+MCP ``voicebox_speak`` calls and the REST ``POST /speak`` route publish
 start/end events that DictateWindow subscribes to via /events/speak, so the
 floating pill surfaces whenever an agent is speaking.
 """

backend/mcp_server/server.py

@@ -27,8 +27,8 @@ def build_mcp_server() -> FastMCP:
     mcp = FastMCP(
         name="voicebox",
         instructions=(
-            "Voicebox is a local voice I/O layer. Use `voicebox.speak` to "
-            "play text in a voice profile, `voicebox.transcribe` for "
+            "Voicebox is a local voice I/O layer. Use `voicebox_speak` to "
+            "play text in a voice profile, `voicebox_transcribe` for "
             "audio→text, and the `list_*` tools to discover profiles and "
             "captures."
         ),

backend/mcp_server/tools.py

@@ -1,8 +1,9 @@
 """Voicebox MCP tool implementations.
 
-Thin wrappers over existing services/routes. Tools are registered with dotted
-names (``voicebox.speak`` etc.) so they look natural in agent logs —
-the Python function name stays snake_case.
+Thin wrappers over existing services/routes. Tools are registered with
+underscore-separated names (``voicebox_speak`` etc.): MCP clients such as
+Claude Desktop validate tool names against ``^[a-zA-Z0-9_-]{1,64}$`` and
+reject the whole tool list if any name contains a dot (#790).
 """
 
 from __future__ import annotations
@@ -202,7 +203,7 @@ def register_tools(mcp: FastMCP) -> None:
         name="voicebox_list_profiles",
         description=(
             "List available voice profiles (both cloned voices and presets). "
-            "Use the returned `name` with voicebox.speak(profile=...)."
+            "Use the returned `name` with voicebox_speak(profile=...)."
         ),
     )
     async def voicebox_list_profiles() -> dict[str, Any]:

backend/models.py

@@ -309,7 +309,7 @@ class GenerationSettingsUpdate(BaseModel):
 
 class MCPClientBindingResponse(BaseModel):
     """Per-MCP-client voice binding — what voice / engine the server should
-    use when a given client_id calls voicebox.speak without args, plus an
+    use when a given client_id calls voicebox_speak without args, plus an
     opt-in personality-rewrite default."""
 
     client_id: str
@@ -346,7 +346,7 @@ class MCPClientBindingListResponse(BaseModel):
 
 
 class SpeakRequest(BaseModel):
-    """Body for POST /speak — non-MCP REST surface that mirrors voicebox.speak."""
+    """Body for POST /speak — non-MCP REST surface that mirrors voicebox_speak."""
 
     text: str = Field(..., min_length=1, max_length=10000)
     profile: Optional[str] = Field(

backend/routes/speak.py

@@ -1,4 +1,4 @@
-"""POST /speak — REST wrapper around voicebox.speak for non-MCP callers.
+"""POST /speak — REST wrapper around voicebox_speak for non-MCP callers.
 
 Shell scripts, ACP, A2A, or any agent that doesn't speak MCP can hit this
 endpoint to play text through a cloned voice. Uses the same profile
@@ -30,7 +30,7 @@ async def speak(
     request: Request,
     db: Session = Depends(get_db),
 ):
-    """Speak text in a voice profile. Mirrors voicebox.speak (MCP).
+    """Speak text in a voice profile. Mirrors voicebox_speak (MCP).
 
     Response shape matches POST /generate — a ``GenerationResponse`` with
     ``status="generating"`` and an ``id`` the caller polls at

backend/tests/test_mcp_speak.py

@@ -1,4 +1,4 @@
-"""Tests for the voicebox.speak MCP tool's ``model_size`` plumbing (issue #884).
+"""Tests for the voicebox_speak MCP tool's ``model_size`` plumbing (issue #884).
 
 The MCP speak path used to build its ``GenerationRequest`` without a
 ``model_size``, so every agent-triggered generation silently fell back to the