kokoro-tts-mcp
Text-to-speech MCP server using the Kokoro-82M model accelerated with MLX on Apple Silicon, enabling local Claude and Codex clients to speak text aloud and convert text to audio.
Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
scottschram
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
speakSpeak text aloud. Returns immediately while audio plays in background.
pausePause current audio playback.
resumeResume paused audio playback.
stopStop any currently-playing audio immediately.
statusReturn current playback state: idle, playing, or paused.
user_stop_requestedCheck if the user stopped playback externally (e.g. Stream Deck button).
speak_and_saveGenerate speech and save to a file. Blocks until file is written.
list_voicesList all available Kokoro voices, grouped by accent and gender.
Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
8/8 tools missing one or more hints — speak (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); pause (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); resume (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +5 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Destructive tools are labelled
3 tools perform destructive updates without destructiveHint — resume deletes at line 453 (os.remove(SENTINEL)); user_stop_requested deletes at line 483 (os.remove(STOP_SENTINEL)); speak_and_save deletes at line 537 (wav_path.unlink(missing_ok=True))
Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.
Descriptions match behaviour
1 tool describes read intent but its handler mutates — user_stop_requested (line 483: os.remove(STOP_SENTINEL))
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
Only 2/8 tool handlers declare input schemas (25%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 2/8 tool handlers wrap calls in try/catch (25%)
Wrap each tool handler body in try/catch and return a structured error response.
Tests exist
No test files found
Add tests that exercise each declared tool.
Tool description accuracy
user_stop_requested: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/scottschram/kokoro-tts-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check